Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedSSM: State Space Model-based Proactive Inference for Heterogeneous Multimodal Federated Learning
Hengyi Ren, Yuchen Xie, Changlong Wang, Xin Li, Yue Huang, Jian Guo, Lijuan Sun
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add decision-aware state space model for proactive client selection (ablation) | FedSSM · VQA v2.0 (alpha 0.1) | rounds to target: 38 -> 22 | Improved |
| add decision-aware SSM (ablation) | FedSSM · VQA v2.0 (alpha 0.1) | accuracy (%): 65.18 -> 68.47 | Improved |
| add counterfactual client selection (ablation) | FedSSM · UCF-101 (alpha 0.1) | accuracy (%): 80.41 -> 82.85 | Improved |
| add surprise-driven adaptive participation budget (ablation) | FedSSM · VQA v2.0 (alpha 0.1) | accuracy (%): 67.15 -> 68.47 | Improved |
| add trust-weighted fusion (ablation) | FedSSM · VQA v2.0 (alpha 0.1) | accuracy (%): 67.62 -> 68.47 | Improved |
| replace random client selection with FedSSM selection (same routing and fusion) (ablation) | FedSSM · UCF-101 (alpha 0.1) | accuracy (%): 77.46 -> 82.85 | Improved |
| use FedSSM over FedMBridge | FedSSM · Hateful Memes (alpha 0.1) | AUC-ROC (%): 61.24 -> 65.72 | Improved |
| use FedSSM over FedMBridge for communication | FedSSM · VQA v2.0 (alpha 0.1) | communication cost to 65% accuracy (GB): 2.16 -> 1.14 | Improved |
| use Oort or CriticalFL utility-based selection over FedAvg | FedAvg · VQA v2.0 (alpha 0.1) | accuracy (%): 58.42 -> 61.35 (Oort), 63.72 (CriticalFL) | Improved |
| raise partial-modality ratio to 75% (ablation) | FedSSM · VQA v2.0 (alpha 0.1) | accuracy (%): approximately 10% decline (FedAvg over 20%) | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FedMBridge — FedMBridge: Bridgeable Multimodal Federated Learning (ICML 2024) · better on 9 of 9 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning (NeurIPS 2026 · similarity 0.88)
- Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning (NeurIPS 2024 · similarity 0.88)
- Reinforcement Active Client Selection for Federated Heterogeneous Graph Learning (AAAI 2025 · similarity 0.86)
- FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation (NeurIPS 2026 · similarity 0.86)
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.86)
- FedECADO: A Dynamical System Model of Federated Learning (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
