Graphgpt: Graph instruction tuning for large language models
Graph Neural Networks (GNNs) have advanced graph structure understanding via recursive
information exchange and aggregation among graph nodes. To improve model robustness …
information exchange and aggregation among graph nodes. To improve model robustness …
Contrastive cross-scale graph knowledge synergy
Graph representation learning via Contrastive Learning (GCL) has drawn considerable
attention recently. Efforts are mainly focused on gathering more global information via …
attention recently. Efforts are mainly focused on gathering more global information via …
Disentangled multiplex graph representation learning
Unsupervised multiplex graph representation learning (UMGRL) has received increasing
interest, but few works simultaneously focused on the common and private information …
interest, but few works simultaneously focused on the common and private information …
I'm me, we're us, and i'm us: Tri-directional contrastive learning on hypergraphs
Although machine learning on hypergraphs has attracted considerable attention, most of the
works have focused on (semi-) supervised learning, which may cause heavy labeling costs …
works have focused on (semi-) supervised learning, which may cause heavy labeling costs …
[PDF][PDF] CONGREGATE: Contrastive Graph Clustering in Curvature Spaces.
Graph clustering is a longstanding research topic, and has achieved remarkable success
with the deep learning methods in recent years. Nevertheless, we observe that several …
with the deep learning methods in recent years. Nevertheless, we observe that several …
Homogcl: Rethinking homophily in graph contrastive learning
Contrastive learning (CL) has become the de-facto learning paradigm in self-supervised
learning on graphs, which generally follows the" augmenting-contrasting''learning scheme …
learning on graphs, which generally follows the" augmenting-contrasting''learning scheme …
Sterling: Synergistic representation learning on bipartite graphs
A fundamental challenge of bipartite graph representation learning is how to extract
informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to …
informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to …
KRACL: Contrastive learning with graph context modeling for sparse knowledge graph completion
Knowledge Graph Embeddings (KGE) aim to map entities and relations to low dimensional
spaces and have become the de-facto standard for knowledge graph completion. Most …
spaces and have become the de-facto standard for knowledge graph completion. Most …
MentorGNN: Deriving Curriculum for Pre-Training GNNs
Graph pre-training strategies have been attracting a surge of attention in the graph mining
community, due to their flexibility in parameterizing graph neural networks (GNNs) without …
community, due to their flexibility in parameterizing graph neural networks (GNNs) without …
Improving augmentation consistency for graph contrastive learning
Graph contrastive learning (GCL) enhances unsupervised graph representation by
generating different contrastive views, in which properties of augmented nodes are required …
generating different contrastive views, in which properties of augmented nodes are required …