{"total":17,"rows":[{"id":"2106.02743","title":"SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks","created":"2021-06-04","cited_by_count":30,"area":null},{"id":"2305.13854","title":"The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2304.00897","title":"Accuracy is not the only Metric that matters: Estimating the Energy Consumption of Deep Learning Models","created":"2023-04-03","cited_by_count":9,"area":null},{"id":"2407.09324","title":"Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization","created":"2024-07-12","cited_by_count":6,"area":null},{"id":"2104.11805","title":"Partitioning sparse deep neural networks for scalable training and inference","created":"2021-04-23","cited_by_count":4,"area":null},{"id":"2503.07505","title":"From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2308.04762","title":"Tram-FL: Routing-based Model Training for Decentralized Federated Learning","created":"2023-08-09","cited_by_count":3,"area":null},{"id":"2211.00889","title":"Accelerating Parallel Stochastic Gradient Descent via Non-blocking Mini-batches","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2606.22768","title":"Factored Gossip DiLoCo: Reducing Blocking Communication in DiLoCo","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2103.07454","title":"EventGraD: Event-Triggered Communication in Parallel Machine Learning","created":"2021-03-12","cited_by_count":1,"area":null},{"id":"2211.00839","title":"RCD-SGD: Resource-Constrained Distributed SGD in Heterogeneous Environment via Submodular Partitioning","created":"2022-11-02","cited_by_count":1,"area":null},{"id":"2404.19749","title":"Scale-Robust Timely Asynchronous Decentralized Learning","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2405.11389","title":"Adjacent Leader Decentralized Stochastic Gradient Descent","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2411.17866","title":"Distributed Sign Momentum with Local Steps for Training Transformers","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2506.09769","title":"Load-Aware Training Scheduling for Model Circulation-based Decentralized Federated Learning","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2406.02565","title":"Sequence-to-sequence models in peer-to-peer learning: A practical application","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2609.08476","title":"When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}