Abstract: Graph Transformers, emerging as a new architecture for graph representation learning, suffer from the quadratic complexity and can only handle graphs with at most thousands of nodes. To this ...

Abstract: Graph Contrastive Learning (GCL) has significantly advanced graph representation learning by generating more effective node embeddings. It aims to create informative representations by ...

The Black Hole (BH) strategy is a novel graph sparsification technique inspired by the gravitational pull of black holes, which condense matter into highly structured forms. BH retains the most ...

This repository contains the official implementation of the paper "Boosting Graph Neural Networks via Adaptive Knowledge Distillation". This work proposes a novel knowledge distillation framework for ...