AutoCoG: A Unified Data-Model Co-Search Framework for Graph Neural NetworksDownload PDF

25 Feb 2022, 12:35 (edited 24 Jun 2022)AutoML-Conf 2022 (Main Track)Readers: Everyone
  • Abstract: Neural architecture search (NAS) has demonstrated success in discovering promising architectures for vision or language modeling tasks, and it has recently been introduced to searching for graph neural networks (GNNs) as well. Despite the preliminary success, GNNs struggle in dealing with heterophily or low-homophily graphs where connected nodes may have different class labels and dissimilar features. To this end, we propose co-optimizing both the input graph topology and the model's architecture topology simultaneously. That yields AutoCoG, the first unified data-model co-search NAS framework for GNNs. By defining a highly flexible data-model co-search space, AutoCoG is gracefully formulated as a principled bi-level optimization that can be end-to-end solved by the differentiable search methods. Experiments show AutoCoG achieves gains of up to 4% for Actor, 7.3% on average for Web datasets, 0.17% for CoAuthor-CS, and finally 5.4% for Wikipedia-Photo benchmarks. All codes will be released upon paper acceptance.
  • Keywords: GCN, NAS
  • One-sentence Summary: We propose AutoCoG, a NAS framework to unified model's architecture search and graph-augmentation in a differentiable manner.
  • Track: Main track
  • Reproducibility Checklist: Yes
  • Broader Impact Statement: Yes
  • Paper Availability And License: Yes
  • Code Of Conduct: Yes
  • Reviewers: duc hoang,
  • Main Paper And Supplementary Material: pdf
  • CPU Hours: 0
  • GPU Hours: 48
  • TPU Hours: 0
  • Evaluation Metrics: No
  • Estimated CO2e Footprint: 5.18
  • Class Of Approaches: Gradient-based Methods, Progressive Search
  • Datasets And Benchmarks: WebKB-Texas, WebKB-Wisconsin, WebKB-Cornell, CoAuthor-CS, CoAuthor-Physics, Amazon-Photos, Amazon-Computers, Actor
  • Performance Metrics: Accuracy
  • Benchmark Performance: Actor 38.04 Texas 80.27 Wisconsin 80.39 Cornell 64.86 Computer 78.91 CS 92.05 Photos 85.16 Physics 93.28
5 Replies