发表机构
Sun Yat-sen University（中山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FedSocket通过共享Q接口实现接收方可执行的联邦知识交换，在异构多模态场景下显著提升缺失模态准确率，并验证了联合推理优于独立集成。
AI 中文摘要
联邦知识必须能够被具有不同模态、私有架构和任务的接收方所使用。我们提出了FedSocket，它将接收方执行作为交换模型的设计要求。一个共享的Q结合了接收方可计算的输入、任务拥有的输出和所有权感知的聚合，通过一个共同的预测接口连接异构的私有模型。私有模型训练本地的Q副本；返回的Q支持本地学习和联合推理，仅交换Q参数和计数。在六个数据集上，FedSocket在MELD和UCF-51上将缺失模态的接收方准确率分别比Local提高了14.44和15.51个百分点。在匹配的推理能力下，Joint在UCF-51准确率上超过独立集成11.06个百分点，在平均双向Flickr30k R@1上超过4.87个百分点。Joint在所有四个异构端点上也比仅使用Q有所改进，证明了结合本地和交换预测的价值。教师控制、共享路径干预和组件因子分析确定了监督、共享和部署的作用。FedSocket使交换的知识从联邦训练到接收方推理直接可用。
英文摘要
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.
Comments17 figures
