6 citations · 7 across the 5 of their papers we have counts for
7 papers
Rethinking Graph Generalization through the Lens of Sharpness-Aware Minimization
Yang Qiu, Yixiong Zou, Jun Wang
Graph Neural Networks (GNNs) have achieved remarkable success across various graph-based tasks but remain highly sensitive to distribution shifts. In this work, we focus on a preva…
Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization
Yang Qiu, Yixiong Zou, Jun Wang +3
Out-of-distribution generalization under distributional shifts remains a critical challenge for graph neural networks. Existing methods generally adopt the Invariant Risk Minimizat…
PAGE: Parametric Generative Explainer for Graph Neural Network
Yang Qiu, Wei Liu, Jun Wang +1
This article introduces PAGE, a parameterized generative interpretive framework. PAGE is capable of providing faithful explanations for any graph neural network without necessitati…
What makes math problems hard for reinforcement learning: a case study
Ali Shehper, Anibal M. Medina-Mardones, Lucas Fagan +6
Using a long-standing conjecture from combinatorial group theory, we explore, from multiple perspectives, the challenges of finding rare instances carrying disproportionately high…
D-Separation for Causal Self-Explanation
Wei Liu, Jun Wang, Haozhao Wang +4
Rationalization is a self-explaining framework for NLP models. Conventional work typically uses the maximum mutual information (MMI) criterion to find the rationale that is most in…
Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint
Wei Liu, Jun Wang, Haozhao Wang +5
A self-explaining rationalization model is generally constructed by a cooperative game where a generator selects the most human-intelligible pieces from the input text as rationale…
MGR: Multi-generator Based Rationalization
Wei Liu, Haozhao Wang, Jun Wang +4
Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input…