Reinforcement Learning Enhanced Explainer for Graph Neural Networks
Dec 6, 2021
Speakers
Caihua Shan
Speaker · 0 followers
Yifei Shen
Speaker · 0 followers
Dongsheng Li
Speaker · 0 followers
About
Graph neural networks (GNNs) have recently emerged as revolutionary technologies for machine learning tasks on graphs. In GNNs, the graph structure is generally incorporated with node representation via the message passing scheme, making the explanation much more challenging. Given a trained GNN model, a GNN explainer aims to identify a most influential subgraph to interpret the prediction of an instance (e.g., a node or a graph), which is essentially a combinatorial optimization problem over graph. The existing works solve this problem by continuous relaxation or search-based heuristics. But they suffer from key issues such as violation of message passing and hand-crafted heuristics, leading to inferior interpretability. To address these issues, we propose a RL-enhanced GNN explainer, RG-Explainer, which consists of three main components: starting point selection, iterative graph generation and stopping criteria learning. RG-Explainer could construct a connected explanatory subgraph by sequentially adding nodes from the boundary of the current generated graph, which is consistent with the message passing scheme. Further, we design an effective seed locator to select the starting point, and learn stopping criteria to generate superior explanations. Extensive experiments on both synthetic and real datasets show that RG-Explainer outperforms state-of-the-art GNN explainers. Moreover, RG-Explainer can be applied in the inductive setting, demonstrating its better generalization ability.Graph neural networks (GNNs) have recently emerged as revolutionary technologies for machine learning tasks on graphs. In GNNs, the graph structure is generally incorporated with node representation via the message passing scheme, making the explanation much more challenging. Given a trained GNN model, a GNN explainer aims to identify a most influential subgraph to interpret the prediction of an instance (e.g., a node or a graph), which is essentially a combinatorial optimization problem over gr…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Conformal Bayesian Computation
Watch later
Edwin Fong, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
An Empirical Investigation of Model-to-Model Distribution Shifts in Trained Convolutional Filters
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
The Causal-Neural Connection: Expressiveness, Learnability, and Inference
Watch later
Kevin Xia, …
Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%
Iterative Connecting Probability Estimation for Networks
Watch later
Yichen Qin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Math AI for Education (MATHAI4ED): Bridging the Gap Between Research and Smart Education
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Deciphering antibody affinity maturation with language models and weakly supervised learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%