Graph structure learning is a well-established problem that aims at
opti...
Graph neural networks have been extensively studied for learning with
in...
Learning on graphs, where instance nodes are inter-connected, has become...
Real-world data generation often involves complex inter-dependencies amo...
Graph neural networks (GNNs), as the de-facto model class for representa...
We study a new paradigm of knowledge transfer that aims at encoding grap...
The goal of sequential event prediction is to estimate the next event ba...
Collaborative filtering (CF), as a standard method for recommendation wi...
We target open-world feature extrapolation problem where the feature spa...
We introduce a conceptually simple yet effective model for self-supervis...
Data sparsity and cold-start issues emerge as two major bottlenecks for
...
We target modeling latent dynamics in high-dimension marked event sequen...
Deep generative models are generally categorized into explicit models an...
Social recommendation leverages social information to solve data sparsit...