MOTIF-Driven Contrastive Learning of Graph Representations

AAAI 2021 pp. 15980-15981

doi:10.1609/AAAI.V35I18.17986 /aaai/2021/subramonian2021aaai-motif/

Abstract

We propose a MOTIF-driven contrastive framework to pretrain a graph neural network in a self-supervised manner so that it can automatically mine motifs from large graph datasets. Our framework achieves state-of-the-art results on various graph-level downstream tasks with few labels, like molecular property prediction.

PDF AAAI Semantic Scholar

Cite

Text

Subramonian. "MOTIF-Driven Contrastive Learning of Graph Representations." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17986

Markdown

[Subramonian. "MOTIF-Driven Contrastive Learning of Graph Representations." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/subramonian2021aaai-motif/) doi:10.1609/AAAI.V35I18.17986

BibTeX

@inproceedings{subramonian2021aaai-motif,
  title     = {{MOTIF-Driven Contrastive Learning of Graph Representations}},
  author    = {Subramonian, Arjun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15980-15981},
  doi       = {10.1609/AAAI.V35I18.17986},
  url       = {https://mlanthology.org/aaai/2021/subramonian2021aaai-motif/}
}