dorsal/arxiv
View SchemaPID-Guided Partial Alignment for Multimodal Decentralized Federated Learning
| Authors | Yanhang Shi, Xiaoyu Wang, Houwei Cao, Jian Li, Yong Liu |
|---|---|
| Categories | |
| ArXiv ID | 2601.10012vv1 |
| URL | https://arxiv.org/abs/2601.10012 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Multimodal decentralized federated learning (DFL) is challenging because agents differ in available modalities and model architectures, yet must collaborate over peer-to-peer (P2P) networks without a central coordinator. Standard multimodal pipelines learn a single shared embedding across all modalities. In DFL, such a monolithic representation induces gradient misalignment between uni- and multimodal agents; as a result, it suppresses heterogeneous sharing and cross-modal interaction. We present PARSE, a multimodal DFL framework that operationalizes partial information decomposition (PID) in a server-free setting. Each agent performs feature fission to factorize its latent representation into redundant, unique, and synergistic slices. P2P knowledge sharing among heterogeneous agents is enabled by slice-level partial alignment: only semantically shareable branches are exchanged among agents that possess the corresponding modality. By removing the need for central coordination and gradient surgery, PARSE resolves uni-/multimodal gradient conflicts, thereby overcoming the multimodal DFL dilemma while remaining compatible with standard DFL constraints. Across benchmarks and agent mixes, PARSE yields consistent gains over task-, modality-, and hybrid-sharing DFL baselines. Ablations on fusion operators and split ratios, together with qualitative visualizations, further demonstrate the efficiency and robustness of the proposed design.
{
"annotation_id": "a5eb7810-6106-41da-92b9-a2422689fd05",
"date_created": "2026-02-17T05:53:23.546000Z",
"date_modified": "2026-02-17T05:53:23.546000Z",
"file_hash": "b45c622797fbf88166c9e908ca5eef029818f9aab317bb2deffcf7849654c4e9",
"private": false,
"record": {
"abstract": "Multimodal decentralized federated learning (DFL) is challenging because agents differ in available modalities and model architectures, yet must collaborate over peer-to-peer (P2P) networks without a central coordinator. Standard multimodal pipelines learn a single shared embedding across all modalities. In DFL, such a monolithic representation induces gradient misalignment between uni- and multimodal agents; as a result, it suppresses heterogeneous sharing and cross-modal interaction. We present PARSE, a multimodal DFL framework that operationalizes partial information decomposition (PID) in a server-free setting. Each agent performs feature fission to factorize its latent representation into redundant, unique, and synergistic slices. P2P knowledge sharing among heterogeneous agents is enabled by slice-level partial alignment: only semantically shareable branches are exchanged among agents that possess the corresponding modality. By removing the need for central coordination and gradient surgery, PARSE resolves uni-/multimodal gradient conflicts, thereby overcoming the multimodal DFL dilemma while remaining compatible with standard DFL constraints. Across benchmarks and agent mixes, PARSE yields consistent gains over task-, modality-, and hybrid-sharing DFL baselines. Ablations on fusion operators and split ratios, together with qualitative visualizations, further demonstrate the efficiency and robustness of the proposed design.",
"arxiv_id": "2601.10012",
"authors": [
"Yanhang Shi",
"Xiaoyu Wang",
"Houwei Cao",
"Jian Li",
"Yong Liu"
],
"categories": [
"cs.LG"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "PID-Guided Partial Alignment for Multimodal Decentralized Federated Learning",
"url": "https://arxiv.org/abs/2601.10012",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "1304361b-f069-4cff-bbff-882c27417795",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}