no code implementations • NeurIPS 2021 • Louis-Pascal A. C. Xhonneux, Andreea Deac, Petar Velickovic, Jian Tang
Due to the fundamental differences between algorithmic reasoning knowledge and feature extractors such as used in Computer Vision or NLP, we hypothesise that standard transfer techniques will not be sufficient to achieve systematic generalisation.
no code implementations • 25 Sep 2019 • Andreea Deac, Yu-Hsiang Huang, Petar Velickovic, Pietro Lio, Jian Tang
Through many recent advances in graph representation learning, performance achieved on tasks involving graph-structured data has substantially increased in recent years---mostly on tasks involving node-level predictions.