相关论文: I'm Me, We're Us, and I'm Us: Tri-directional Cont…

Recent contrastive learning methods have shown to be effective in various tasks, learning generalizable representations invariant to data augmentation thereby leading to state of the art performances. Regarding the multifaceted nature of…

Graph representation learning has attracted a surge of interest recently, whose target at learning discriminant embedding for each node in the graph. Most of these representation methods focus on supervised learning and heavily depend on…

Existing contrastive learning methods rely on pairwise sample contrast $z_x^\top z_{x'}$ to learn data representations, but the learned features often lack clear interpretability from a human perspective. Theoretically, it lacks feature…

Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances and maximizes the distance between dissimilar ones in the…

Contrastive learning (CL) has become a dominant paradigm for self-supervised hypergraph learning, enabling effective training without costly labels. However, node entities in real-world hypergraphs are often associated with rich textual…

Recent advancements in Graph Contrastive Learning (GCL) have demonstrated remarkable effectiveness in improving graph representations. However, relying on predefined augmentations (e.g., node dropping, edge perturbation, attribute masking)…

Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. Most existing HGNN-based approaches are supervised or semi-supervised learning methods requiring graphs to be…

Heterogeneous graphs (HGs) are composed of multiple types of nodes and edges, making it more effective in capturing the complex relational structures inherent in the real world. However, in real-world scenarios, labeled data is often…

We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner. GraphCL learns node embeddings by maximizing the similarity between the representations of two randomly…

Graph contrastive learning (CL) methods learn node representations in a self-supervised manner by maximizing the similarity between the augmented node representations obtained via a GNN-based encoder. However, CL methods perform poorly on…

Recently, contrastive learning (CL) has emerged as a successful method for unsupervised graph representation learning. Most graph CL methods first perform stochastic augmentation on the input graph to obtain two graph views and maximize the…

Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance…

Supervised learning, while prevalent for information cascade modeling, often requires abundant labeled data in training, and the trained model is not easy to generalize across tasks and datasets. It often learns task-specific…

We introduce a self-supervised approach for learning node and graph level representations by contrasting structural views of graphs. We show that unlike visual representation learning, increasing the number of views to more than two or…

Hypergraphs can model higher-order relationships among data objects that are found in applications such as social networks and bioinformatics. However, recent studies on hypergraph learning that extend graph convolutional networks to…

In this work, we aim to consider the application of contrastive learning in the scenario of the recommendation system adequately, making it more suitable for recommendation task. We propose a learning paradigm called supervised contrastive…

Graph contrastive learning (GCL), as a self-supervised learning method, can solve the problem of annotated data scarcity. It mines explicit features in unannotated graphs to generate favorable graph representations for downstream tasks.…

Generalizable, transferrable, and robust representation learning on graph-structured data remains a challenge for current graph neural networks (GNNs). Unlike what has been developed for convolutional neural networks (CNNs) for image data,…

Contrastive learning has emerged as a powerful tool for graph representation learning. However, most contrastive learning methods learn features of graphs with fixed coarse-grained scale, which might underestimate either local or global…

Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data. Meanwhile, most existing representation learning methods embed the heterogeneous…