Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Self-supervised learning has gained popularity because of its ability to avoid the cost of
annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as …

Recently, graph collaborative filtering methods have been proposed as an effective
recommendation approach, which can capture users' preference over items by modeling the …

Text embeddings are useful features in many applications such as semantic search and
computing text similarity. Previous work typically trains models customized for different use …

This paper presents SimCSE, a simple contrastive learning framework that greatly advances
state-of-the-art sentence embeddings. We first describe an unsupervised approach, which …

Learning high-quality sentence representations benefits a wide range of natural language
processing tasks. Though BERT-based pre-trained language models achieve high …

We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence
embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference …

Recent research demonstrates the effectiveness of using fine-tuned language models~(LM)
for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily …

Pre-trained language models have proven their unique powers in capturing implicit
language features. However, most pre-training approaches focus on the word-level training …

In recent years, graph neural networks (GNNs) have emerged as a successful tool in a
variety of graph-related applications. However, the performance of GNNs can be …