diff --git a/README.md b/README.md index 2e942af..7f9b9a2 100644 --- a/README.md +++ b/README.md @@ -62,7 +62,7 @@ This section partially refers to [DBLP](https://dblp.uni-trier.de/search?q=Feder |Title | Affiliation | Venue | Year | TL;DR | Materials| | ------------------------------------------------------------ | ---------------------- | ---- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | -|Federated Visualization: A Privacy-Preserving Strategy for Aggregated Visual Query. | ZJU | IEEE Trans. Vis. Comput. Graph. :mortar_board: | 2023 | | [pub](https://ieeexplore.ieee.org/document/10083324) [pdf](https://arxiv.org/abs/2007.15227) | +| Federated Visualization: A Privacy-Preserving Strategy for Aggregated Visual Query. | ZJU | IEEE Trans. Vis. Comput. Graph. :mortar_board: | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/10083324)] [[PDF](https://arxiv.org/abs/2007.15227)] | | Personalized Subgraph Federated Learning | KAIST | ICML :mortar_board: | 2023 | FED-PUB[^FED-PUB] | [[PDF](https://arxiv.org/abs/2206.10206)] | | Semi-decentralized Federated Ego Graph Learning for Recommendation | SUST | WWW:mortar_board: | 2023 | | [[PUB](https://dl.acm.org/doi/10.1145/3543507.3583337)] [[PDF](https://arxiv.org/abs/2302.10900)] | | Federated Graph Neural Network for Fast Anomaly Detection in Controller Area Networks | ECUST | IEEE Trans. Inf. Forensics Secur. :mortar_board: | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/10026810)] | @@ -70,22 +70,22 @@ This section partially refers to [DBLP](https://dblp.uni-trier.de/search?q=Feder | HetVis: A Visual Analysis Approach for Identifying Data Heterogeneity in Horizontal Federated Learning | Nankai University | IEEE Trans. Vis. Comput. Graph. :mortar_board: | 2023 | HetVis[^HetVis] | [[PUB](https://ieeexplore.ieee.org/document/9912364)] [[PDF](https://arxiv.org/abs/2208.07491)] | | Federated Learning on Non-IID Graphs via Structural Knowledge Sharing | UTS | AAAI :mortar_board: | 2023 | FedStar[^FedStar] | [[PDF](https://arxiv.org/abs/2211.13009)] [[CODE](https://github.com/yuetan031/fedstar)] | | FedGS: Federated Graph-based Sampling with Arbitrary Client Availability | XMU | AAAI :mortar_board: | 2023 | FedGS[^FedGS] | [[PDF](https://arxiv.org/abs/2211.13975)] [[CODE](https://github.com/wwzzz/fedgs)] | -| An Information Theoretic Perspective for Heterogeneous Subgraph Federated Learning. | PKU | DASFAA | 2023 | | [pub](https://link.springer.com/chapter/10.1007/978-3-031-30637-2_50) | -| GraphCS: Graph-based client selection for heterogeneity in federated learning | NUDT | J. Parallel Distributed Comput. | 2023 | | [pub](https://www.sciencedirect.com/science/article/abs/pii/S0743731523000394?via%3Dihub) | -| Towards On-Device Federated Learning: A Direct Acyclic Graph-based Blockchain Approach | BUPT | IEEE Trans. Neural Networks Learn. Syst. | 2023 | |[pub](https://ieeexplore.ieee.org/document/9524833) [[PDF](https://arxiv.org/abs/2104.13092)] | +| An Information Theoretic Perspective for Heterogeneous Subgraph Federated Learning. | PKU | DASFAA | 2023 | | [[PUB](https://link.springer.com/chapter/10.1007/978-3-031-30637-2_50)] | +| GraphCS: Graph-based client selection for heterogeneity in federated learning | NUDT | J. Parallel Distributed Comput. | 2023 | | [[PUB](https://www.sciencedirect.com/science/article/abs/pii/S0743731523000394?via%3Dihub)] | +| Towards On-Device Federated Learning: A Direct Acyclic Graph-based Blockchain Approach | BUPT | IEEE Trans. Neural Networks Learn. Syst. | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/9524833)] [[PDF](https://arxiv.org/abs/2104.13092)] | | Short-Term Traffic Flow Prediction Based on Graph Convolutional Networks and Federated Learning | ZUEL | IEEE Trans. Intell. Transp. Syst. | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/9794333)] | | Hyper-Graph Attention Based Federated Learning Methods for Use in Mental Health Detection. | HVL | IEEE J. Biomed. Health Informatics | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/9767700)] | | Federated Learning-Based Cross-Enterprise Recommendation With Graph Neural | | IEEE Trans. Ind. Informatics | 2023 | FL-GMT[^FL-GMT] | [[PUB](https://ieeexplore.ieee.org/document/9873989)] | -| Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learning | ZJUT | IEEE Trans. Comput. Soc. Syst. | 2023 | |[[PUB](https://ieeexplore.ieee.org/document/9745270)] [[PDF](https://arxiv.org/abs/2110.06468)] [[CODE](https://github.com/hgh0545/graph-fraudster)] | -| ESA-FedGNN: Efficient secure aggregation for federated graph neural networks. | | Peer Peer Netw. Appl. | 2023 | |[pub](https://link.springer.com/article/10.1007/s12083-023-01472-2) | -| FedCKE: Cross-Domain Knowledge Graph Embedding in Federated Learning | SWJTU | IEEE Trans. Big Data | 2023 | |[pub](https://ieeexplore.ieee.org/document/9887815) | -| Asynchronous federated learning with directed acyclic graph-based blockchain in edge computing: Overview, design, and challenges. | | Expert Syst. Appl. | 2023 | |[pub](https://www.sciencedirect.com/science/article/abs/pii/S0957417423003974?via%3Dihub) | +| Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learning | ZJUT | IEEE Trans. Comput. Soc. Syst. | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/9745270)] [[PDF](https://arxiv.org/abs/2110.06468)] [[CODE](https://github.com/hgh0545/graph-fraudster)] | +| ESA-FedGNN: Efficient secure aggregation for federated graph neural networks. | | Peer Peer Netw. Appl. | 2023 | | [[PUB](https://link.springer.com/article/10.1007/s12083-023-01472-2)] | +| FedCKE: Cross-Domain Knowledge Graph Embedding in Federated Learning | SWJTU | IEEE Trans. Big Data | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/9887815)] | +| Asynchronous federated learning with directed acyclic graph-based blockchain in edge computing: Overview, design, and challenges. | | Expert Syst. Appl. | 2023 | | [[PUB](https://www.sciencedirect.com/science/article/abs/pii/S0957417423003974?via%3Dihub)] | | FedGR: Federated Graph Neural Network for Recommendation System | CUPT | Axioms | 2023 | | [[PUB](https://www.mdpi.com/2075-1680/12/2/170)] | -| S-Glint: Secure Federated Graph Learning With Traffic Throttling and Flow Scheduling. | | IEEE Trans. Green Commun. Netw. | 2023 | | [pub](https://ieeexplore.ieee.org/document/9810521) | -| FedAGCN: A traffic flow prediction framework based on federated learning and Asynchronous Graph Convolutional Network | | Appl. Soft Comput. | 2023 | | [pub](https://www.sciencedirect.com/science/article/abs/pii/S156849462300193X?via%3Dihub) | +| S-Glint: Secure Federated Graph Learning With Traffic Throttling and Flow Scheduling. | | IEEE Trans. Green Commun. Netw. | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/9810521)] | +| FedAGCN: A traffic flow prediction framework based on federated learning and Asynchronous Graph Convolutional Network | | Appl. Soft Comput. | 2023 | | [[PUB](https://www.sciencedirect.com/science/article/abs/pii/S156849462300193X?via%3Dihub)] | | GDFed: Dynamic Federated Learning for Heterogenous Device Using Graph Neural Network | KHU | ICOIN | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/10048926)] [[CODE](https://github.com/IntelligentNetworkingLAB/Graph-Neural-Network-based-Federated-Learning-for-Heterogenous-Device-Network)] | | Coordinated Scheduling and Decentralized Federated Learning Using Conflict Clustering Graphs in Fog-Assisted IoD Networks | UBC | IEEE Trans. Veh. Technol. | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/9932020)] | -| FedRule: Federated Rule Recommendation System with Graph Neural Networks | CMU | IoTDI | 2023 | FedRule[^FedRule] | [pub](https://dl.acm.org/doi/10.1145/3576842.3582328) [[PDF](https://arxiv.org/abs/2211.06812)] | +| FedRule: Federated Rule Recommendation System with Graph Neural Networks | CMU | IoTDI | 2023 | FedRule[^FedRule] | [[PUB](https://dl.acm.org/doi/10.1145/3576842.3582328)] [[PDF](https://arxiv.org/abs/2211.06812)] | | FedWalk: Communication Efficient Federated Unsupervised Node Embedding with Differential Privacy | SJTU | KDD :mortar_board: | 2022 | FedWalk[^FedWalk] | [[PUB](https://dl.acm.org/doi/10.1145/3534678.3539308)] [[PDF](https://arxiv.org/abs/2205.15896)] | | FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Platform for Federated Graph Learning :fire: | Alibaba | KDD (Best Paper Award) :mortar_board: | 2022 | FederatedScope-GNN[^FederatedScope-GNN] | [[PDF](https://arxiv.org/abs/2204.05562)] [[CODE](https://github.com/alibaba/FederatedScope)] [[PUB](https://dl.acm.org/doi/10.1145/3534678.3539112)] | | Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning | SJTU | ICML :mortar_board: | 2022 | GAMF[^GAMF] | [[PUB](https://proceedings.mlr.press/v162/liu22k/liu22k.pdf)] [[CODE](https://github.com/Thinklab-SJTU/GAMF)] | @@ -111,7 +111,7 @@ This section partially refers to [DBLP](https://dblp.uni-trier.de/search?q=Feder | Federated Graph Learning with Periodic Neighbour Sampling | HKU | IWQoS | 2022 | PNS-FGL[^PNS-FGL] | [[PUB](https://ieeexplore.ieee.org/document/9812908)] | | FedGSL: Federated Graph Structure Learning for Local Subgraph Augmentation. | | Big Data | 2022 | | [[PUB](https://ieeexplore.ieee.org/document/10020771/)] | | Domain-Aware Federated Social Bot Detection with Multi-Relational Graph Neural Networks. | UCAS; CAS | IJCNN | 2022 | DA-MRG[^DA-MRG] | [[PUB](https://ieeexplore.ieee.org/document/9892366)] | -| A Federated Multi-Server Knowledge Graph Embedding Framework For Link Prediction. | | ICTAI | 2022 | | [pub](https://ieeexplore.ieee.org/document/10097981) | +| A Federated Multi-Server Knowledge Graph Embedding Framework For Link Prediction. | | ICTAI | 2022 | | [[PUB](https://ieeexplore.ieee.org/document/10097981)] | | A Privacy-Preserving Subgraph-Level Federated Graph Neural Network via Differential Privacy | Ping An Technology | KSEM | 2022 | DP-FedRec[^DP-FedRec] | [[PUB](https://link.springer.com/chapter/10.1007/978-3-031-10989-8_14)] [[PDF](https://arxiv.org/abs/2206.03492)] | | Clustered Graph Federated Personalized Learning. | NTNU | IEEECONF | 2022 | | [[PUB](https://ieeexplore.ieee.org/document/10051979)] | | FedGCN: Convergence and Communication Tradeoffs in Federated Training of Graph Convolutional Networks | CMU | CIKM Workshop (Oral) | 2022 | FedGCN[^FedGCN] | [[PDF](https://arxiv.org/abs/2201.12433)] [[CODE](https://github.com/yh-yao/FedGCN)] | @@ -160,9 +160,9 @@ This section partially refers to [DBLP](https://dblp.uni-trier.de/search?q=Feder | SGNN: A Graph Neural Network Based Federated Learning Approach by Hiding Structure | SDU | BigData | 2019 | SGNN[^SGNN] | [[PUB](https://ieeexplore.ieee.org/document/9005983)] [[PDF](https://www.researchgate.net/profile/Shijun_Liu3/publication/339482514_SGNN_A_Graph_Neural_Network_Based_Federated_Learning_Approach_by_Hiding_Structure/links/5f48365d458515a88b790595/SGNN-A-Graph-Neural-Network-Based-Federated-Learning-Approach-by-Hiding-Structure.pdf)] | | Towards Federated Graph Learning for Collaborative Financial Crimes Detection | IBM | NeurIPS Workshop | 2019 | FGL-DFC[^FGL-DFC] | [[PDF](https://arxiv.org/abs/1909.12946)] | | Federated learning of predictive models from federated Electronic Health Records :star: | BU | Int. J. Medical Informatics | 2018 | cPDS[^cPDS] | [[PUB](https://www.sciencedirect.com/science/article/abs/pii/S138650561830008X?via%3Dihub)] | -| FedHGN: A Federated Framework for Heterogeneous Graph Neural Networks. | | preprint | 2023 | | [pdf](https://arxiv.org/abs/2305.09729) [code](https://github.com/cynricfu/FedHGN) | -| Graph-guided Personalization for Federated Recommendation. | | preprint | 2023 | | [pdf](https://arxiv.org/abs/2305.07866) | -| GraphGANFed: A Federated Generative Framework for Graph-Structured Molecules Towards Efficient Drug Discovery. | | preprint | 2023 | | [pdf](https://arxiv.org/abs/2304.05498) | +| FedHGN: A Federated Framework for Heterogeneous Graph Neural Networks. | | preprint | 2023 | | [[PDF](https://arxiv.org/abs/2305.09729)] [[CODE](https://github.com/cynricfu/FedHGN)] | +| Graph-guided Personalization for Federated Recommendation. | | preprint | 2023 | | [[PDF](https://arxiv.org/abs/2305.07866)] | +| GraphGANFed: A Federated Generative Framework for Graph-Structured Molecules Towards Efficient Drug Discovery. | | preprint | 2023 | | [[PDF](https://arxiv.org/abs/2304.05498)] | | GLASU: A Communication-Efficient Algorithm for Federated Learning with Vertically Distributed Graph Data | | preprint | 2023 | | [[PDF](https://arxiv.org/abs/2303.09531)] | | Vertical Federated Graph Neural Network for Recommender System | | preprint | 2023 | | [[PDF](https://arxiv.org/abs/2303.05786)] [[CODE](https://github.com/maiph123/verticalgnn)] | | Lumos: Heterogeneity-aware Federated Graph Learning over Decentralized Devices | | preprint | 2023 | | [[PDF](https://arxiv.org/abs/2303.00492)] | @@ -229,9 +229,9 @@ This section refers to [DBLP](https://dblp.org/search?q=federate%20tree%7Cboost% | Incentive-boosted Federated Crowdsourcing | SDU | AAAI :mortar_board: | 2023 | iFedCrowd[^iFedCrowd] | [[PDF](https://arxiv.org/abs/2211.14439)] | | Explaining predictions and attacks in federated learning via random forests | Universitat Rovira i Virgili | Appl. Intell. | 2023 | | [[PUB](https://link.springer.com/article/10.1007/s10489-022-03435-1)] [[CODE](https://github.com/RamiHaf/Explainable-Federated-Learning-via-Random-Forests)] | | Boosting Accuracy of Differentially Private Federated Learning in Industrial IoT With Sparse Responses | | IEEE Trans. Ind. Informatics | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/9743613)] | -| Driver Drowsiness EEG Detection Based on Tree Federated Learning and Interpretable Network. | | Int. J. Neural Syst. | 2023 | | [pub](https://www.worldscientific.com/doi/10.1142/S0129065723500090) | -| FDPBoost: Federated differential privacy gradient boosting decision trees. | | J. Inf. Secur. Appl. | 2023 | | [pub](https://www.sciencedirect.com/science/article/abs/pii/S2214212623000522?via%3Dihub) | -| Gradient-less Federated Gradient Boosting Trees with Learnable Learning Rates. | | EuroMLSys | 2023 | | [pub](https://dl.acm.org/doi/10.1145/3578356.3592579) [pdf](https://arxiv.org/abs/2304.07537) | +| Driver Drowsiness EEG Detection Based on Tree Federated Learning and Interpretable Network. | | Int. J. Neural Syst. | 2023 | | [[PUB](https://www.worldscientific.com/doi/10.1142/S0129065723500090)] | +| FDPBoost: Federated differential privacy gradient boosting decision trees. | | J. Inf. Secur. Appl. | 2023 | | [[PUB](https://www.sciencedirect.com/science/article/abs/pii/S2214212623000522?via%3Dihub)] | +| Gradient-less Federated Gradient Boosting Trees with Learnable Learning Rates. | | EuroMLSys | 2023 | | [[PUB](https://dl.acm.org/doi/10.1145/3578356.3592579)] [[PDF](https://arxiv.org/abs/2304.07537)] | | HT-Fed-GAN: Federated Generative Model for Decentralized Tabular Data Synthesis | HIT | Entropy | 2023 | | [[PUB](https://www.mdpi.com/1099-4300/25/1/88)] | | Blockchain-Based Swarm Learning for the Mitigation of Gradient Leakage in Federated Learning | University of Udine | IEEE Access | 2023 | | [[PUB](https://ieeexplore.ieee.org/document/10047894)] | | OpBoost: A Vertical Federated Tree Boosting Framework Based on Order-Preserving Desensitization | ZJU | Proc. VLDB Endow. :mortar_board: | 2022 | OpBoost[^OpBoost] | [[PUB](https://www.vldb.org/pvldb/volumes/16/paper/OpBoost%3A%20A%20Vertical%20Federated%20Tree%20Boosting%20Framework%20Based%20on%20Order-Preserving%20Desensitization)] [[PDF](https://arxiv.org/abs/2210.01318)] [[CODE](https://github.com/alibaba-edu/mpc4j/tree/main/mpc4j-sml-opboost)] | @@ -243,10 +243,10 @@ This section refers to [DBLP](https://dblp.org/search?q=federate%20tree%7Cboost% | Federated Learning for Tabular Data using TabNet: A Vehicular Use-Case | | ICCP | 2022 | | [[PUB](https://ieeexplore.ieee.org/document/10053975)] | | Federated Learning for Tabular Data: Exploring Potential Risk to Privacy | Newcastle University | ISSRE | 2022 | | [[PDF](https://arxiv.org/abs/2210.06856)] | | Federated Random Forests can improve local performance of predictive models for various healthcare applications | University of Marburg | Bioinform. | 2022 | FRF[^FRF] | [[PUB](https://academic.oup.com/bioinformatics/article-abstract/38/8/2278/6525214)] [[CODE](https://featurecloud.ai/)] | -| FLForest: Byzantine-robust Federated Learning through Isolated Forest | NUAA | ICPADS | 2022 | | [pub](https://ieeexplore.ieee.org/document/10077947) | +| FLForest: Byzantine-robust Federated Learning through Isolated Forest | NUAA | ICPADS | 2022 | | [[PUB](https://ieeexplore.ieee.org/document/10077947)] | | Boosting the Federation: Cross-Silo Federated Learning without Gradient Descent. | unito | IJCNN | 2022 | federation-boosting[^federation-boosting] | [[PUB](https://ieeexplore.ieee.org/document/9892284)] [[CODE](https://github.com/ml-unito/federation_boosting)] | | Federated Forest | JD | TBD | 2022 | FF[^FF] | [[PUB](https://ieeexplore.ieee.org/document/9088965)] [[PDF](https://arxiv.org/abs/1905.10053)] | -| Sliding Focal Loss for Class Imbalance Classification in Federated XGBoost. | Swinburne University of Technology | ISPA/BDCloud/SocialCom/SustainCom | 2022 | | [pub](https://ieeexplore.ieee.org/document/10070688) | +| Sliding Focal Loss for Class Imbalance Classification in Federated XGBoost. | Swinburne University of Technology | ISPA/BDCloud/SocialCom/SustainCom | 2022 | | [[PUB](https://ieeexplore.ieee.org/document/10070688)] | | Neural gradient boosting in federated learning for hemodynamic instability prediction: towards a distributed and scalable deep learning-based solution. | | AMIA | 2022 | | [[PUB](https://knowledge.amia.org/76677-amia-1.4637602/f006-1.4642154/f006-1.4642155/917-1.4642324/604-1.4642321?qr=1)] | | Fed-GBM: a cost-effective federated gradient boosting tree for non-intrusive load monitoring | The University of Sydney | e-Energy | 2022 | Fed-GBM[^Fed-GBM] | [[PUB](https://dl.acm.org/doi/10.1145/3538637.3538840)] | | Verifiable Privacy-Preserving Scheme Based on Vertical Federated Random Forest | NUST | IEEE Internet Things J. | 2022 | VPRF[^VPRF] | [[PUB](https://ieeexplore.ieee.org/document/9461157)] | @@ -278,8 +278,8 @@ This section refers to [DBLP](https://dblp.org/search?q=federate%20tree%7Cboost% | Straggler Remission for Federated Learning via Decentralized Redundant Cayley Tree | Stevens Institute of Technology | LATINCOM | 2020 | DRC-tree[^DRC-tree] | [[PUB](https://ieeexplore.ieee.org/document/9282334)] | | Federated Soft Gradient Boosting Machine for Streaming Data | Sinovation Ventures AI Institute | Federated Learning | 2020 | Fed-sGBM[^Fed-sGBM] | [[PUB](https://link.springer.com/chapter/10.1007/978-3-030-63076-8_7)] [[解读](https://www.leiphone.com/category/academic/4tVdYDuYTA293NCy.html)] | | Federated Learning of Deep Neural Decision Forests | Fraunhofer-Chalmers Centre | LOD | 2019 | FL-DNDF[^FL-DNDF] | [[PUB](https://link.springer.com/chapter/10.1007/978-3-030-37599-7_58)] | -| Privet: A Privacy-Preserving Vertical Federated Learning Service for Gradient Boosted Decision Tables. | | preprint | 2023 | | [pdf](https://arxiv.org/abs/2305.12652) | -| V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection. | | preprint | 2023 | | [pdf](https://arxiv.org/abs/2305.11654) | +| Privet: A Privacy-Preserving Vertical Federated Learning Service for Gradient Boosted Decision Tables. | | preprint | 2023 | | [[PDF](https://arxiv.org/abs/2305.12652)] | +| V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection. | | preprint | 2023 | | [[PDF](https://arxiv.org/abs/2305.11654)] | | GTV: Generating Tabular Data via Vertical Federated Learning | | preprint | 2023 | | [[PDF](https://arxiv.org/abs/2302.01706)] | | Federated Survival Forests | | preprint | 2023 | | [[PDF](https://arxiv.org/abs/2302.02807)] | | Fed-TDA: Federated Tabular Data Augmentation on Non-IID Data | HIT | preprint | 2022 | Fed-TDA[^Fed-TDA] | [[PDF](https://arxiv.org/abs/2211.13116)] | @@ -1574,6 +1574,7 @@ Many thanks :heart: to the other awesome list: [^FedStar]: From real-world graph datasets, we observe that some structural properties are shared by various domains, presenting great potential for sharing structural knowledge in FGL. Inspired by this, we propose FedStar, an FGL framework that extracts and shares the common underlying structure information for inter-graph federated learning tasks. To explicitly extract the structure information rather than encoding them along with the node features, we define structure embeddings and encode them with an independent structure encoder. Then, the structure encoder is shared across clients while the feature-based knowledge is learned in a personalized way, making FedStar capable of capturing more structure-based domain-invariant information and avoiding feature misalignment issues. We perform extensive experiments over both cross-dataset and cross-domain non-IID FGL settings. 从现实世界的图数据集中，我们观察到一些结构属性被不同的领域所共享，这为联邦图机器学习中共享结构知识提供了巨大的潜力。受此启发，我们提出了FedStar，一个为图间联合学习任务提取和分享共同基础结构信息的FGL框架。为了明确地提取结构信息，而不是将其与节点特征一起编码，我们定义了结构嵌入，并用一个独立的结构编码器对其进行编码。然后，结构编码器在客户之间共享，而基于特征的知识则以个性化的方式学习，这使得FedStar能够捕获更多基于结构的领域变量信息，并避免了特征错位问题。我们在跨数据集和跨域的非IID FGL设置上进行了广泛的实验。 [^FedGS]: Federated Graph-based Sampling (FedGS) to stabilize the global model update and mitigate the long-term bias given arbitrary client availability simultaneously. First, we model the data correlations of clients with a Data-Distribution-Dependency Graph (3DG) that helps keep the sampled clients data apart from each other, which is theoretically shown to improve the approximation to the optimal model update. Second, constrained by the far-distance in data distribution of the sampled clients, we further minimize the variance of the numbers of times that the clients are sampled, to mitigate long-term bias. 基于图的联合采样（Federated Graph-based Sampling，FedGS）稳定了全局模型的更新，并同时减轻了任意客户端可用性的长期偏差。首先，我们用数据分布-依赖图（3DG）对客户的数据相关性进行建模，这有助于使被采样的客户数据相互分离，理论上证明这可以提高对最佳模型更新的近似度。其次，受制于被抽样客户数据分布的远距离，我们进一步将客户被抽样次数的方差降到最低，以减轻长期偏差。 [^FL-GMT]: TBC +[^FedRule]: TBC [^FedWalk]: FedWalk, a random-walk-based unsupervised node embedding algorithm that operates in such a node-level visibility graph with raw graph information remaining locally. FedWalk，一个基于随机行走的无监督节点嵌入算法，在这样一个节点级可见度图中操作，原始图信息保留在本地。 [^FederatedScope-GNN]: FederatedScope-GNN present an easy-to-use FGL (federated graph learning) package. FederatedScope-GNN提出了一个易于使用的FGL（联邦图学习）软件包。 [^GAMF]: GAMF formulate the model fusion problem as a graph matching task, considering the second-order similarity of model weights instead of previous work merely formulating model fusion as a linear assignment problem. For the rising problem scale and multi-model consistency issues, GAMF propose an efficient graduated assignment-based model fusion method, iteratively updates the matchings in a consistency-maintaining manner. GAMF将模型融合问题表述为图形匹配任务，考虑了模型权重的二阶相似性，而不是之前的工作仅仅将模型融合表述为一个线性赋值问题。针对问题规模的扩大和多模型的一致性问题，GAMF提出了一种高效的基于分级赋值的模型融合方法，以保持一致性的方式迭代更新匹配结果。 @@ -1637,7 +1638,6 @@ Many thanks :heart: to the other awesome list: [^FGL-DFC]: To detect financial misconduct, A methodology to share key information across institutions by using a federated graph learning platform that enables us to build more accurate machine learning models by leveraging federated learning and also graph learning approaches. We demonstrated that our federated model outperforms local model by 20% with the UK FCA TechSprint data set. 为了检测财务不当行为，一种通过使用联邦图学习平台在机构间共享关键信息的方法，使我们能够通过利用联邦学习和图学习方法来构建更准确的机器学习模型。 我们证明了我们的联邦模型在英国 FCA TechSprint 数据集上的性能优于本地模型 20%。 [^cPDS]: We aim at solving a binary supervised classification problem to predict hospitalizations for cardiac events using a distributed algorithm. We focus on the soft-margin l1-regularized sparse Support Vector Machine (sSVM) classifier. We develop an iterative cluster Primal Dual Splitting (cPDS) algorithm for solving the large-scale sSVM problem in a decentralized fashion. 我们的目标是解决一个二元监督分类问题，以使用分布式算法预测心脏事件的住院情况。 我们专注于软边距 l1 正则化稀疏支持向量机 (sSVM) 分类器。 我们开发了一种迭代集群 Primal Dual Splitting (cPDS) 算法，用于以分散的方式解决大规模 sSVM 问题。 [^GFL-APPNP]: We first formulate the Graph Federated Learning (GFL) problem that unifies LoG(Learning on Graphs) and FL(Federated Learning) in multi-client systems and then propose sharing hidden representation instead of the raw data of neighbors to protect data privacy as a solution. To overcome the biased gradient problem in GFL, we provide a gradient estimation method and its convergence analysis under the non-convex objective. 我们首先在多客户机系统中统一LoG(在图上学习)和FL (Federation Learning)的图联邦学习(Graph Federation Learning，GFL)问题，然后提出共享隐藏表示代替邻居的原始数据以保护数据隐私作为解决方案。为了克服GFL中的有偏梯度问题，我们给出了非凸目标下的梯度估计方法及其收敛性分析。 -[^FedRule]: TBC [^M3FGM]: TBC [^FedEgo]: FedEgo, a federated graph learning framework based on ego-graphs, where each client will train their local models while also contributing to the training of a global model. FedEgo applies GraphSAGE over ego-graphs to make full use of the structure information and utilizes Mixup for privacy concerns. To deal with the statistical heterogeneity, we integrate personalization into learning and propose an adaptive mixing coefficient strategy that enables clients to achieve their optimal personalization. FedEgo是一个基于自中心图的联邦图学习框架，每个客户端将训练他们的本地模型，同时也为全局模型的训练作出贡献。FedEgo在自中心图上应用GraphSAGE来充分利用结构信息，并利用Mixup来解决隐私问题。为了处理统计上的异质性，我们将个性化整合到学习中，并提出了一个自适应混合系数策略，使客户能够实现其最佳的个性化。 [^FGCL]: TBC diff --git a/data.yaml b/data.yaml index 893a0cd..e9f05e5 100644 --- a/data.yaml +++ b/data.yaml @@ -30,6 +30,15 @@ fl-on-graph-data-and-graph-neural-network: tldr: 60 materials: 60 body: + - title: 'Federated Visualization: A Privacy-Preserving Strategy for Aggregated + Visual Query.' + affiliation: ZJU + venue: 'IEEE Trans. Vis. Comput. Graph. :mortar_board:' + year: '2023' + tldr: '' + materials: + PUB: https://ieeexplore.ieee.org/document/10083324 + PDF: https://arxiv.org/abs/2007.15227 - title: Personalized Subgraph Federated Learning affiliation: KAIST venue: 'ICML :mortar_board:' @@ -111,6 +120,30 @@ fl-on-graph-data-and-graph-neural-network: materials: PDF: https://arxiv.org/abs/2211.13975 CODE: https://github.com/wwzzz/fedgs + - title: An Information Theoretic Perspective for Heterogeneous Subgraph Federated + Learning. + affiliation: PKU + venue: DASFAA + year: '2023' + tldr: '' + materials: + PUB: https://link.springer.com/chapter/10.1007/978-3-031-30637-2_50 + - title: 'GraphCS: Graph-based client selection for heterogeneity in federated learning' + affiliation: NUDT + venue: J. Parallel Distributed Comput. + year: '2023' + tldr: '' + materials: + PUB: https://www.sciencedirect.com/science/article/abs/pii/S0743731523000394?via%3Dihub + - title: 'Towards On-Device Federated Learning: A Direct Acyclic Graph-based Blockchain + Approach' + affiliation: BUPT + venue: IEEE Trans. Neural Networks Learn. Syst. + year: '2023' + tldr: '' + materials: + PUB: https://ieeexplore.ieee.org/document/9524833 + PDF: https://arxiv.org/abs/2104.13092 - title: Short-Term Traffic Flow Prediction Based on Graph Convolutional Networks and Federated Learning affiliation: ZUEL @@ -134,6 +167,38 @@ fl-on-graph-data-and-graph-neural-network: tldr: 'FL-GMT: TBC' materials: PUB: https://ieeexplore.ieee.org/document/9873989 + - title: 'Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical + Federated Learning' + affiliation: ZJUT + venue: IEEE Trans. Comput. Soc. Syst. + year: '2023' + tldr: '' + materials: + PUB: https://ieeexplore.ieee.org/document/9745270 + PDF: https://arxiv.org/abs/2110.06468 + CODE: https://github.com/hgh0545/graph-fraudster + - title: 'ESA-FedGNN: Efficient secure aggregation for federated graph neural networks.' + affiliation: '' + venue: Peer Peer Netw. Appl. + year: '2023' + tldr: '' + materials: + PUB: https://link.springer.com/article/10.1007/s12083-023-01472-2 + - title: 'FedCKE: Cross-Domain Knowledge Graph Embedding in Federated Learning' + affiliation: SWJTU + venue: IEEE Trans. Big Data + year: '2023' + tldr: '' + materials: + PUB: https://ieeexplore.ieee.org/document/9887815 + - title: 'Asynchronous federated learning with directed acyclic graph-based blockchain + in edge computing: Overview, design, and challenges.' + affiliation: '' + venue: Expert Syst. Appl. + year: '2023' + tldr: '' + materials: + PUB: https://www.sciencedirect.com/science/article/abs/pii/S0957417423003974?via%3Dihub - title: 'FedGR: Federated Graph Neural Network for Recommendation System' affiliation: CUPT venue: Axioms @@ -141,6 +206,22 @@ fl-on-graph-data-and-graph-neural-network: tldr: '' materials: PUB: https://www.mdpi.com/2075-1680/12/2/170 + - title: 'S-Glint: Secure Federated Graph Learning With Traffic Throttling and Flow + Scheduling.' + affiliation: '' + venue: IEEE Trans. Green Commun. Netw. + year: '2023' + tldr: '' + materials: + PUB: https://ieeexplore.ieee.org/document/9810521 + - title: 'FedAGCN: A traffic flow prediction framework based on federated learning + and Asynchronous Graph Convolutional Network' + affiliation: '' + venue: Appl. Soft Comput. + year: '2023' + tldr: '' + materials: + PUB: https://www.sciencedirect.com/science/article/abs/pii/S156849462300193X?via%3Dihub - title: 'GDFed: Dynamic Federated Learning for Heterogenous Device Using Graph Neural Network' affiliation: KHU @@ -158,6 +239,14 @@ fl-on-graph-data-and-graph-neural-network: tldr: '' materials: PUB: https://ieeexplore.ieee.org/document/9932020 + - title: 'FedRule: Federated Rule Recommendation System with Graph Neural Networks' + affiliation: CMU + venue: IoTDI + year: '2023' + tldr: 'FedRule: TBC' + materials: + PUB: https://dl.acm.org/doi/10.1145/3576842.3582328 + PDF: https://arxiv.org/abs/2211.06812 - title: 'FedWalk: Communication Efficient Federated Unsupervised Node Embedding with Differential Privacy' affiliation: SJTU @@ -495,6 +584,13 @@ fl-on-graph-data-and-graph-neural-network: Aware检测方法，以提高检测性能。具体来说，DA-MRG利用用户的特征和关系构建多关系图，通过图嵌入获得用户表示，并通过领域感知分类器区分机器人和人类。同时，考虑到不同社交网络中机器人行为之间的相似性，我们认为在它们之间共享数据可以提高检测性能。然而，用户的数据隐私需要严格保护。为了克服这个问题，我们实现了一个面向DA-MRG的联邦学习框架研究，以实现不同社交网络之间的数据共享，同时保护数据隐私。' materials: PUB: https://ieeexplore.ieee.org/document/9892366 + - title: A Federated Multi-Server Knowledge Graph Embedding Framework For Link Prediction. + affiliation: '' + venue: ICTAI + year: '2022' + tldr: '' + materials: + PUB: https://ieeexplore.ieee.org/document/10097981 - title: A Privacy-Preserving Subgraph-Level Federated Graph Neural Network via Differential Privacy affiliation: Ping An Technology @@ -1202,6 +1298,29 @@ fl-on-graph-data-and-graph-neural-network: 算法，用于以分散的方式解决大规模 sSVM 问题。' materials: PUB: https://www.sciencedirect.com/science/article/abs/pii/S138650561830008X?via%3Dihub + - title: 'FedHGN: A Federated Framework for Heterogeneous Graph Neural Networks.' + affiliation: '' + venue: preprint + year: '2023' + tldr: '' + materials: + PDF: https://arxiv.org/abs/2305.09729 + CODE: https://github.com/cynricfu/FedHGN + - title: Graph-guided Personalization for Federated Recommendation. + affiliation: '' + venue: preprint + year: '2023' + tldr: '' + materials: + PDF: https://arxiv.org/abs/2305.07866 + - title: 'GraphGANFed: A Federated Generative Framework for Graph-Structured Molecules + Towards Efficient Drug Discovery.' + affiliation: '' + venue: preprint + year: '2023' + tldr: '' + materials: + PDF: https://arxiv.org/abs/2304.05498 - title: 'GLASU: A Communication-Efficient Algorithm for Federated Learning with Vertically Distributed Graph Data' affiliation: '' @@ -1262,13 +1381,6 @@ fl-on-graph-data-and-graph-neural-network: Learning)的图联邦学习(Graph Federation Learning，GFL)问题，然后提出共享隐藏表示代替邻居的原始数据以保护数据隐私作为解决方案。为了克服GFL中的有偏梯度问题，我们给出了非凸目标下的梯度估计方法及其收敛性分析。' materials: PDF: https://arxiv.org/abs/2212.12158 - - title: 'FedRule: Federated Rule Recommendation System with Graph Neural Networks' - affiliation: CMU - venue: preprint - year: '2022' - tldr: 'FedRule: TBC' - materials: - PDF: https://arxiv.org/abs/2211.06812 - title: M3FGM:a node masking and multi-granularity message passing-based federated graph model for spatial-temporal data prediction affiliation: Xidian University @@ -1390,15 +1502,6 @@ fl-on-graph-data-and-graph-neural-network: materials: PDF: https://arxiv.org/abs/2111.06750 CODE: https://github.com/jw9msjwjnpdrlfw/tsfl - - title: 'Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical - Federated Learning' - affiliation: '' - venue: preprint - year: '2021' - tldr: '' - materials: - PDF: https://arxiv.org/abs/2110.06468 - CODE: https://github.com/hgh0545/graph-fraudster - title: 'PPSGCN: A Privacy-Preserving Subgraph Sampling Based Distributed GCN Training Method' affiliation: '' @@ -1451,14 +1554,6 @@ fl-on-graph-data-and-graph-neural-network: tldr: 'FL-AGCNS: TBC' materials: PDF: https://arxiv.org/abs/2104.04141 - - title: 'Towards On-Device Federated Learning: A Direct Acyclic Graph-based Blockchain - Approach' - affiliation: '' - venue: preprint - year: '2021' - tldr: '' - materials: - PDF: https://arxiv.org/abs/2104.13092 - title: A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian Regularization affiliation: '' @@ -1567,6 +1662,30 @@ fl-on-tabular-data: tldr: '' materials: PUB: https://ieeexplore.ieee.org/document/9743613 + - title: Driver Drowsiness EEG Detection Based on Tree Federated Learning and Interpretable + Network. + affiliation: '' + venue: Int. J. Neural Syst. + year: '2023' + tldr: '' + materials: + PUB: https://www.worldscientific.com/doi/10.1142/S0129065723500090 + - title: 'FDPBoost: Federated differential privacy gradient boosting decision trees.' + affiliation: '' + venue: J. Inf. Secur. Appl. + year: '2023' + tldr: '' + materials: + PUB: https://www.sciencedirect.com/science/article/abs/pii/S2214212623000522?via%3Dihub + - title: Gradient-less Federated Gradient Boosting Trees with Learnable Learning + Rates. + affiliation: '' + venue: EuroMLSys + year: '2023' + tldr: '' + materials: + PUB: https://dl.acm.org/doi/10.1145/3578356.3592579 + PDF: https://arxiv.org/abs/2304.07537 - title: 'HT-Fed-GAN: Federated Generative Model for Decentralized Tabular Data Synthesis' affiliation: HIT @@ -1672,6 +1791,13 @@ fl-on-tabular-data: materials: PUB: https://academic.oup.com/bioinformatics/article-abstract/38/8/2278/6525214 CODE: https://featurecloud.ai/ + - title: 'FLForest: Byzantine-robust Federated Learning through Isolated Forest' + affiliation: NUAA + venue: ICPADS + year: '2022' + tldr: '' + materials: + PUB: https://ieeexplore.ieee.org/document/10077947 - title: 'Boosting the Federation: Cross-Silo Federated Learning without Gradient Descent.' affiliation: unito @@ -1700,6 +1826,13 @@ fl-on-tabular-data: materials: PUB: https://ieeexplore.ieee.org/document/9088965 PDF: https://arxiv.org/abs/1905.10053 + - title: Sliding Focal Loss for Class Imbalance Classification in Federated XGBoost. + affiliation: Swinburne University of Technology + venue: ISPA/BDCloud/SocialCom/SustainCom + year: '2022' + tldr: '' + materials: + PUB: https://ieeexplore.ieee.org/document/10070688 - title: 'Neural gradient boosting in federated learning for hemodynamic instability prediction: towards a distributed and scalable deep learning-based solution.' affiliation: '' @@ -2071,6 +2204,22 @@ fl-on-tabular-data: can be computed which some/several federated learning algorithms utilize. 深度神经决策森林（DNDF），将分治策略与属性表示学习结合起来。通过对森林预测节点的概率分布进行参数化，并将森林中的所有树木纳入损失函数中，可以计算出整个森林的梯度，一些/一些联邦学习算法利用了这一梯度。' materials: PUB: https://link.springer.com/chapter/10.1007/978-3-030-37599-7_58 + - title: 'Privet: A Privacy-Preserving Vertical Federated Learning Service for Gradient + Boosted Decision Tables.' + affiliation: '' + venue: preprint + year: '2023' + tldr: '' + materials: + PDF: https://arxiv.org/abs/2305.12652 + - title: V2X-Boosted Federated Learning for Cooperative Intelligent Transportation + Systems with Contextual Client Selection. + affiliation: '' + venue: preprint + year: '2023' + tldr: '' + materials: + PDF: https://arxiv.org/abs/2305.11654 - title: 'GTV: Generating Tabular Data via Vertical Federated Learning' affiliation: '' venue: preprint