Abstract Pretrained Foundation Models (PFMs) are regarded as the foundation for various
downstream tasks across different data modalities. A PFM (eg, BERT, ChatGPT, GPT-4) is …

Graph representation learning aims to effectively encode high-dimensional sparse graph-
structured data into low-dimensional dense vectors, which is a fundamental task that has …

Graphs can model complex relationships between objects, enabling a myriad of Web
applications such as online page/article classification and social recommendation. While …

Self-supervised learning (SSL) has been extensively explored in recent years. Particularly,
generative SSL has seen emerging success in natural language processing and other …

Collaborative Filtering (CF) has emerged as fundamental paradigms for parameterizing
users and items into latent representation space, with their correlative patterns from …

We present modality gap, an intriguing geometric phenomenon of the representation space
of multi-modal models. Specifically, we show that different data modalities (eg images and …

In recent years, neural architecture-based recommender systems have achieved
tremendous success, but they still fall short of expectation when dealing with highly sparse …

The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

Despite the promising representation learning of graph neural networks (GNNs), the
supervised training of GNNs notoriously requires large amounts of labeled data from each …

Graph neural networks, a powerful deep learning tool to model graph-structured data, have
demonstrated remarkable performance on numerous graph learning tasks. To address the …