Evaluating post-hoc explanations for graph neural networks via robustness analysis
This work studies the evaluation of explaining graph neural networks (GNNs), which is
crucial to the credibility of post-hoc explainability in practical usage. Conventional evaluation …
crucial to the credibility of post-hoc explainability in practical usage. Conventional evaluation …
Factorized explainer for graph neural networks
Graph Neural Networks (GNNs) have received increasing attention due to their ability to
learn from graph-structured data. To open the black-box of these deep learning models, post …
learn from graph-structured data. To open the black-box of these deep learning models, post …
Regexplainer: Generating explanations for graph neural networks in regression task
Graph regression is a fundamental task and has received increasing attention in a wide
range of graph learning tasks. However, the inference process is often not interpretable …
range of graph learning tasks. However, the inference process is often not interpretable …
Towards mitigating dimensional collapse of representations in collaborative filtering
Contrastive Learning (CL) has shown promising performance in collaborative filtering. The
key idea is to use contrastive loss to generate augmentation-invariant embeddings by …
key idea is to use contrastive loss to generate augmentation-invariant embeddings by …
On regularization for explaining graph neural networks: An information theory perspective
This work studies the explainability of graph neural networks (GNNs), which is important for
the credibility of GNNs in practical usage. Existing mask-based explanation methods mostly …
the credibility of GNNs in practical usage. Existing mask-based explanation methods mostly …
Graph Convolutional Networks With Adaptive Neighborhood Awareness
M Guang, C Yan, Y Xu, J Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Graph convolutional networks (GCNs) can quickly and accurately learn graph
representations and have shown powerful performance in many graph learning domains …
representations and have shown powerful performance in many graph learning domains …
A Graph is Worth Words: Euclideanizing Graph using Pure Transformer
Can we model non-Euclidean graphs as pure language or even Euclidean vectors while
retaining their inherent information? The non-Euclidean property have posed a long term …
retaining their inherent information? The non-Euclidean property have posed a long term …
Interpreting Graph Neural Networks with In-Distributed Proxies
Graph Neural Networks (GNNs) have become a building block in graph data processing,
with wide applications in critical domains. The growing needs to deploy GNNs in high-stakes …
with wide applications in critical domains. The growing needs to deploy GNNs in high-stakes …
REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretability
Understanding the agent's learning process, particularly the factors that contribute to its
success or failure post-training, is crucial for comprehending the rationale behind the agent's …
success or failure post-training, is crucial for comprehending the rationale behind the agent's …
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
We investigate the problem of explainability in machine learning. To address this problem,
Feature Attribution Methods (FAMs) measure the contribution of each feature through a …
Feature Attribution Methods (FAMs) measure the contribution of each feature through a …