{"ID":2832719,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.06154","arxiv_id":"2512.06154","title":"Learning Invariant Graph Representations Through Redundant Information","abstract":"Learning invariant graph representations for out-of-distribution (OOD) generalization remains challenging because the learned representations often retain spurious components. To address this challenge, this work introduces a new tool from information theory called Partial Information Decomposition (PID) that goes beyond classical information-theoretic measures. We identify limitations in existing approaches for invariant representation learning that solely rely on classical information-theoretic measures, motivating the need to precisely focus on redundant information about the target $Y$ shared between spurious subgraphs $G_s$ and invariant subgraphs $G_c$ obtained via PID. Next, we propose a new multi-level optimization framework that we call -- Redundancy-guided Invariant Graph learning (RIG) -- that maximizes redundant information while isolating spurious and causal subgraphs, enabling OOD generalization under diverse distribution shifts. Our approach relies on alternating between estimating a lower bound of redundant information (which itself requires an optimization) and maximizing it along with additional objectives. Experiments on both synthetic and real-world graph datasets demonstrate the generalization capabilities of our proposed RIG framework.","short_abstract":"Learning invariant graph representations for out-of-distribution (OOD) generalization remains challenging because the learned representations often retain spurious components. To address this challenge, this work introduces a new tool from information theory called Partial Information Decomposition (PID) that goes beyo...","url_abs":"https://arxiv.org/abs/2512.06154","url_pdf":"https://arxiv.org/pdf/2512.06154v1","authors":"[\"Barproda Halder\",\"Pasan Dissanayake\",\"Sanghamitra Dutta\"]","published":"2025-12-05T21:07:11Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.IT\"]","methods":"[]","has_code":false}