[2510.05535] Permutation-Invariant Representation Learning for Robust and Privacy-Preserving Feature Selection

Computer Science > Machine Learning arXiv:2510.05535 (cs) [Submitted on 7 Oct 2025 (v1), last revised 27 Feb 2026 (this version, v3)] Title:Permutation-Invariant Representation Learning for Robust and Privacy-Preserving Feature Selection Authors:Rui Liu, Tao Zhe, Yanjie Fu, Feng Xia, Ted Senator, Dongjie Wang View a PDF of the paper titled Permutation-Invariant Representation Learning for Robust and Privacy-Preserving Feature Selection, by Rui Liu and 5 other authors View PDF HTML (experimental) Abstract:Feature selection eliminates redundancy among features to improve downstream task performance while reducing computational overhead. Existing methods often struggle to capture intricate feature interactions and adapt across diverse application scenarios. Recent advances employ generative intelligence to alleviate these drawbacks. However, these methods remain constrained by permutation sensitivity in embedding and reliance on convexity assumptions in gradient-based search. To address these limitations, our initial work introduces a novel framework that integrates permutation-invariant embedding with policy-guided search. Although effective, it still left opportunities to adapt to realistic distributed scenarios. In practice, data across local clients is highly imbalanced, heterogeneous and constrained by strict privacy regulations, limiting direct sharing. These challenges highlight the need for a framework that can integrate feature selection knowledge across clients with...