# FedSocket: Recipient-Executable Knowledge Exchange for Heterogeneous Multimodal Federated Learning

arXiv: https://arxiv.org/abs/2609.37582 · HTML: https://mlsanity.com/paper/2609.37582/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Balanced Multimodal Learning via On-the-fly Gradient Modulation](https://mlsanity.com/paper/2203.15332/) (2022)
- [FedKD: Communication Efficient Federated Learning via Knowledge Distillation](https://mlsanity.com/paper/2108.13323/) (2021)
- [PMR: Prototypical Modal Rebalance for Multimodal Learning](https://mlsanity.com/paper/2211.07089/) (2022)
- [Multimodal Federated Learning via Contrastive Representation Ensemble](https://mlsanity.com/paper/2302.08888/) (2023)
- [Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning](https://mlsanity.com/paper/2204.12703/) (2022)
- [Federated Mutual Learning](https://mlsanity.com/paper/2006.16765/) (2020)
- [FedMultimodal: A Benchmark For Multimodal Federated Learning](https://mlsanity.com/paper/2306.09486/) (2023)
- [FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion](https://mlsanity.com/paper/2110.11027/) (2021)
- [MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis](https://mlsanity.com/paper/2405.06822/) (2024)
- [Enhanced Multimodal Representation Learning with Cross-modal KD](https://mlsanity.com/paper/2306.07646/) (2023)
- [Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection](https://mlsanity.com/paper/2401.00403/) (2023)
- [Federated Prompt-Tuning with Heterogeneous and Incomplete Multimodal Client Data](https://mlsanity.com/paper/2602.07081/) (2026)
- [FedAFD: Multimodal Federated Learning via Adversarial Fusion and Distillation](https://mlsanity.com/paper/2603.04890/) (2026)
- [TACTFL: Temporal Contrastive Training for Multi-modal Federated Learning with Similarity-guided Model Aggregation](https://mlsanity.com/paper/2509.17532/) (2025)

## Abstract (arXiv)

Federated knowledge must remain usable by recipients with different modalities, private architectures, and tasks. We present FedSocket, which makes recipient execution a design requirement of the exchanged model. A shared Q combines recipient-computable inputs, task-owned outputs, and ownership-aware aggregation, connecting heterogeneous private models through a common prediction interface. Private models teach local Q copies; the returned Q supports local learning and Joint inference, with only Q parameters and counts exchanged. Across six datasets, FedSocket improves missing-modality recipient accuracy over Local by 14.44 and 15.51 percentage points on MELD and UCF-51. Under matched inference capacity, Joint exceeds independent ensembles by 11.06 points in UCF-51 accuracy and 4.87 points in mean bidirectional Flickr30k R@1. Joint also improves over Q alone on all four heterogeneous endpoints, demonstrating the value of combining local and exchanged predictions. Teacher controls, sharing-path interventions, and component factorials identify the roles of supervision, sharing, and deployment. FedSocket makes exchanged knowledge directly usable from federated training to recipient inference.