• Publications
  • Influence
Graph Contrastive Learning with Adaptive Augmentation
TLDR
This paper proposes a novel graph contrastive representation learning method with adaptive augmentation that incorporates various priors for topological and semantic aspects of the graph that consistently outperforms existing state-of-the-art baselines and even surpasses some supervised counterparts.
Deep Graph Contrastive Representation Learning
TLDR
This paper proposes a novel framework for unsupervised graph representation learning by leveraging a contrastive objective at the node level, and generates two graph views by corruption and learns node representations by maximizing the agreement of node representations in these two views.
An Empirical Study of Graph Contrastive Learning
TLDR
This work identifies several critical design considerations within a general GCL paradigm, including augmentation functions, contrasting modes, contrastive objectives, and negative mining techniques, and develops an easy-to-use library PyGCL, featuring modularized CL components, standardized evaluation, and experiment management.
CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning
TLDR
A novel cluster-aware graph neural network (CAGNN) model for unsupervised graph representation learning using self-supervised techniques, which gains over 7% improvements in terms of accuracy on node clustering over state-of-the-arts.
Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction
TLDR
A novel DisentanglEd Self-at-Tentwork (DESTINE) framework for CTR prediction that explicitly decouples the computation of unary feature importance from pairwise interaction and not only maintains computational efficiency but achieves consistent improvements over state-of-the-art baselines.
A Survey on Deep Graph Generation: Methods and Applications
TLDR
A comprehensive review on the existing literature of graph generation from a variety of emerging methods to its wide application areas and divides the state-of-the-art methods into three categories based on model architectures and summarizes their generation strategies.
Structure-Enhanced Heterogeneous Graph Contrastive Learning
TLDR
A novel method to generate multiple semantic views for HGs based on metapaths and advocate the explicit use of structure embedding, which enriches the model with local structural patterns of the underlying HGs, so as to better mine true and hard negatives for GCL.
Implementing path-dependent GADT reasoning for Scala 3
TLDR
This paper shows how the existing constraint-based GADT reasoning of the Scala 3 compiler is extended to also consider path-dependent types, making Scala’s support for G ADT programming more complete and bringing Scala closer to its formal foundations.
Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning
TLDR
This work investigates Contrastive Learning (CL), a key component in self-supervised approaches, on HGs to alleviate the label scarcity problem, and proposes a structure-aware hard negative mining scheme that measures hardness by structural characteristics for HGs.