Meta-multigraph Search: Rethinking Meta-structure on Heterogeneous Information Networks
Not on the map. Why?
Abstract (arXiv)
Meta-structures are widely used to define which subset of neighbors to aggregate information in heterogeneous information networks (HINs). In this work, we investigate existing meta-structures, including meta-path and meta-graph, and observe that they are initially designed manually with fixed patterns and hence are insufficient to encode various rich semantic information on diverse HINs. Through reflection on their limitation, we define a new concept called meta-multigraph as a more expressive and flexible generalization of meta-graph, and propose a stable differentiable search method to automatically optimize the meta-multigraph for specific HINs and tasks. As the flexibility of meta-multigraphs may propagate redundant messages, we further introduce a complex-to-concise (C2C) meta-multigraph that propagates messages from complex to concise along the depth of meta-multigraph. Moreover, we observe that the differentiable search typically suffers from unstable search and a significant gap between the meta-structures in search and evaluation. To this end, we propose a progressive search algorithm by implicitly narrowing the search space to improve search stability and reduce inconsistency. Extensive experiments are conducted on six medium-scale benchmark datasets and one large-scale benchmark dataset over two representative tasks, i.e., node classification and recommendation. Empirical results demonstrate that our search methods can automatically find expressive meta-multigraphs and C2C meta-multigraphs, enabling our model to outperform state-of-the-art heterogeneous graph neural networks.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 34 of its 53 references that are in the map. First posted on arXiv 23 Apr 2023.
Builds on
34 of 53 references.
References · 34
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2018DARTS: Differentiable Architecture Searchcited by 1,782
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
- 2016Complex Embeddings for Simple Link Predictioncited by 897
- 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
- 2019Heterogeneous Graph Attention Networkcited by 732
- 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
- 2020Heterogeneous Graph Transformercited by 581
- 2019Graph Transformer Networkscited by 520
22 more
- 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
- 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
- 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
- 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
- 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
- 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
- 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
- 2022Graph Attention Multi-Layer Perceptroncited by 82
- 2019Auto-GNN: Neural Architecture Search of Graph Neural Networkscited by 73
- 2021Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced trainingcited by 54
- 2021Search to aggregate neighborhood for graph neural networkcited by 48
- 2022PaSca: a Graph Neural Architecture Search System under the Scalable Paradigmcited by 37
- 2020ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Codingcited by 36
- 2020DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networkscited by 34
- 2019Efficient Neural Architecture Search via Proximal Iterationscited by 31
- 2020Scalable Graph Neural Networks for Heterogeneous Graphscited by 31
- 2021Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Searchcited by 27
- 2021Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspectivecited by 19
- 2019Efficient Neural Interaction Function Search for Collaborative Filteringcited by 16
- 2020Neural Architecture Search in Graph Neural Networkscited by 15
- 2021Genetic Meta-Structure Search for Recommendation on Heterogeneous Information Networkcited by 9
- 2022Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networkscited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.