The emergence of large-scale pre-trained language models has revolutionized various AI
research domains. Transformers-based Large Language Models (LLMs) have gradually …

The graph Transformer emerges as a new architecture and has shown superior
performance on various graph mining tasks. In this work, we observe that existing graph …

Many important problems involving molecular property prediction from 3D structures have
limited data, posing a generalization challenge for neural networks. In this paper, we …

Graph Transformer (GT) recently has emerged as a new paradigm of graph learning
algorithms, outperforming the previously popular Message Passing Neural Network (MPNN) …

Most text-driven human motion generation methods employ sequential modeling
approaches, eg, transformer, to extract sentence-level text representations automatically and …

Normalization is known to help the optimization of deep neural networks. Curiously, different
architectures require specialized normalization methods. In this paper, we study what …

In this paper we show that simple noise regularisation can be an effective way to address
GNN oversmoothing. First we argue that regularisers addressing oversmoothing should both …

Abstract Graph Convolutional Networks (GCNs) are known to suffer from performance
degradation as the number of layers increases, which is usually attributed to over …

To bridge the gaps between topology-aware Graph Neural Networks (GNNs) and inference-
efficient Multi-Layer Perceptron (MLPs), GLNN proposes to distill knowledge from a well …

Abstract Multi-Label Text Classification (MLTC) is an important but challenging task in the
field of natural language processing. In this paper, we propose a novel method, Semantic …