This work proposes CausalGCD, a causality-inspired framework designed to mitigate domain-shift bias in category discovery and proposes a Causal Geometric Manifold Constraint that enforces invariant manifold-level associations between known and unknown categories across domains, thereby facilitating robust discovery of novel classes.
CausalShift is proposed, a modular, plugin-based framework for end-to-end dataset shift handling that reduces the in-distribution to out-of-distribution accuracy gap, while remaining competitive on real-world image shift and achieving performance parity with ERM on mild-shift tasks.
Shuang Song, Muhammad Syafiq Mohd Pozi, Nik F. Farid· Applied Sciences· 0 citations
Causal Structure-guided DRO (CS-DRO) is proposed, which estimates a directed acyclic graph (DAG) that encodes the predictive relationships between representations and labels, serving as a proxy for causal structure shared across source domains.
Seonggyeom Kim, Eunjung Choi, Dong-Kyu Chae· Proceedings of the 32nd ACM...· 0 citations
This work introduces a novel inverted causal self-attention mechanism (CSAM) that emphasizes latent and indirect causal relationships by inverting tokens and inducing sparsity in attention scores, focusing on significant causal interactions and reducing spurious correlations.
Yu-Sen Liu, Yong Wang, Yifan Yin et al.· Pacific-Asia Conference on K...· 6 citations
Domain generalization (DG) aims to learn from multiple source domains and generalize to unseen target domains. Most DG methods pursue invariance: they seek a causal representation whose prediction rule is invariant across domains. This principle is effective when the causal mechanism is stable, but becomes restrictive...
Causal Discovery (CD) from observational data faces two fundamental challenges. First, purely statistical methods often lack the power to resolve structural ambiguities in low-sample regimes. Second, although LLM-assisted hybrid approaches improve structure recovery through semantic reasoning, the influence of that rea...
A. Thorat, Ravi Kolla, Vishak K Bhat et al.· 0 citations
This work proposes a unified, causally informed attribution approach that integrates structural causal information into the metric-tree decomposition framework and corrects key sources of misalignment in GCM-based causal attributions, substantially improving causal validity while preserving interpretability and fast co...
Jing Zhou, Dominik Janzing, Sepp Tsang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
