多视角感知中，用基底融合提升分布式学习的表示多样性与准确性。
Compositional Distributed Learning for Multi-View Perception: A Maximal Coding Rate Reduction Perspective
- 基于最大编码率压缩原理，周期性交换截断基矩阵实现子空间融合。
- 实验显示分类准确率高，且表示多样性优于基底相关、表示耦合的基线方法。
- 适合分布式多视角感知场景，尤其关注表示解耦与通信效率的研究者。
本文提出一种基于最大编码率压缩原理与子空间基底融合的组合式分布式学习框架，用于多视角感知。各智能体对自身学习到的子空间进行周期性奇异值分解，并交换截断后的基矩阵，从而获得融合子空间。通过引入投影矩阵并最小化输出与其投影间的距离，强制学习表示逼近融合子空间。理论上证明了编码率变化的迹有界，且基底融合的一致性可保证。数值仿真表明，所提算法在保持表示多样性的同时，达到更高分类准确率，优于基底相关、表示耦合的基线方法。
原文摘要 · Abstract (English)
In this letter, we formulate a compositional distributed learning framework for multi-view perception by leveraging the maximal coding rate reduction principle combined with subspace basis fusion. In the proposed algorithm, each agent conducts a periodic singular value decomposition on its learned subspaces and exchanges truncated basis matrices, based on which the fused subspaces are obtained. By introducing a projection matrix and minimizing the distance between the outputs and its projection, the learned representations are enforced towards the fused subspaces. It is proved that the trace on the coding-rate change is bounded and the consistency of basis fusion is guaranteed theoretically. Numerical simulations validate that the proposed algorithm achieves high classification accuracy while maintaining representations' diversity, compared to baselines showing correlated subspaces and coupled representations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。