Automorphic Equivalence-aware Graph Neural Network
Dec 6, 2021
Speakers
About
Distinguishing the structural equivalence of nodes in a graph plays an essential role in many scientific domains, e.g., computational biologist and social network analysis. However, existing graph neural networks (GNNs) fail to capture such an important property. To make GNN aware of structural equivalence, we first introduce a localized variant of the classic concept — automorphic equivalence (AE). Then, we design a novel variant of GNN, i.e., GRAPE, that uses learnable AE-aware aggregators to explicitly differentiate the structural equivalences of each node's neighbors with the aids of various subgraph templates. To alleviate the barrier of subgraph template design, we also propose to automatically search the design space with an efficient genetic algorithm. Moreover, we theoretically prove that GRAPE is expressive in terms of generating distinct representations for nodes with different AE features, which fills in a fundamental gap of existing GNN variants. Finally, we empirically validate our model on eight real-world graph data, including social network, e-commerce co-purchase network, and citation network, and show that it consistently outperforms strong baselines.Distinguishing the structural equivalence of nodes in a graph plays an essential role in many scientific domains, e.g., computational biologist and social network analysis. However, existing graph neural networks (GNNs) fail to capture such an important property. To make GNN aware of structural equivalence, we first introduce a localized variant of the classic concept — automorphic equivalence (AE). Then, we design a novel variant of GNN, i.e., GRAPE, that uses learnable AE-aware aggregato…
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
GENhance: Deep Extrapolation for Attribute-Enhanced Generation
Watch later
Alvin Chan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Evaluating Approximate Inference in Bayesian Deep Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Similarity and Matching of Neural Network Representations
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Annotation Quality Framework - Accuracy,Credibility, and Consistency
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Solving Math Problems by Joint Parsing and Cognitive Reasoning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Investigating generative neural-network models for building pest insect detectors in sticky trap images for the Peruvian horticulture
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%