LGSep 27, 2023

Graph-level Representation Learning with Joint-Embedding Predictive Architectures

arXiv:2309.16014v317 citationsh-index: 10Has Code
Originality Incremental advance
AI Analysis

It addresses the problem of learning expressive graph representations for machine learning practitioners, offering an incremental improvement by adapting JEPAs to graphs.

The paper tackles graph-level representation learning by proposing Graph-JEPA, a self-supervised method that predicts latent representations of masked subgraphs from context subgraphs, achieving strong performance in downstream tasks like graph classification and regression.

Joint-Embedding Predictive Architectures (JEPAs) have recently emerged as a novel and powerful technique for self-supervised representation learning. They aim to learn an energy-based model by predicting the latent representation of a target signal y from the latent representation of a context signal x. JEPAs bypass the need for negative and positive samples, traditionally required by contrastive learning while avoiding the overfitting issues associated with generative pretraining. In this paper, we show that graph-level representations can be effectively modeled using this paradigm by proposing a Graph Joint-Embedding Predictive Architecture (Graph-JEPA). In particular, we employ masked modeling and focus on predicting the latent representations of masked subgraphs starting from the latent representation of a context subgraph. To endow the representations with the implicit hierarchy that is often present in graph-level concepts, we devise an alternative prediction objective that consists of predicting the coordinates of the encoded subgraphs on the unit hyperbola in the 2D plane. Through multiple experimental evaluations, we show that Graph-JEPA can learn highly semantic and expressive representations, as shown by the downstream performance in graph classification, regression, and distinguishing non-isomorphic graphs. The code is available at https://github.com/geriskenderi/graph-jepa.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes