Many real-world datasets are represented as tensors, i.e., multi-dimensi...
Real-world graphs are dynamic, constantly evolving with new interactions...
Graphs are a powerful mathematical model, and they are used to represent...
A hypergraph is a data structure composed of nodes and hyperedges, where...
Graph neural networks (GNNs) learn the representation of graph-structure...
What are the relations between the edge weights and the topology in
real...
Simplicial complexes are higher-order combinatorial structures which hav...
Many real-world data are naturally represented as a sparse reorderable
m...
Hypergraphs are a powerful abstraction for modeling high-order relations...
Graphs are widely used for modeling various types of interactions, such ...
The Weather4Cast competition (hosted by NeurIPS 2022) required competito...
Continual Learning (CL) is the process of learning ceaselessly a sequenc...
Recently, many deep-learning techniques have been applied to various
wea...
Sets have been used for modeling various types of objects (e.g., a docum...
Although machine learning on hypergraphs has attracted considerable
atte...
Sequences of group interactions, such as emails, online discussions, and...
Hypergraphs (i.e., sets of hyperedges) naturally represent group relatio...
Which one is better between two representative graph summarization model...
Are users of an online social network interested equally in all connecti...
Online recommender systems should be always aligned with users' current
...
Deep learning has been successfully applied to precipitation nowcasting....
A hypergraph is a generalization of an ordinary graph, and it naturally
...
Given a massive graph, how can we exploit its hierarchical structure for...
A variety of tasks on dynamic graphs, including anomaly detection, commu...
Graph neural networks (GNNs) are one of the most popular approaches to u...
Consider traffic data (i.e., triplets in the form of
source-destination-...
Consider multiple seasonal time series being collected in real-time, in ...
Given a dynamic graph stream, how can we detect the sudden appearance of...
Graph Neural Networks (GNNs) have received massive attention in the fiel...
Given a stream of graph edges from a dynamic graph, how can we assign an...
Given a fully dynamic graph, represented as a stream of edge insertions ...
Given a graph G and the desired size k in bits, how can we summarize G w...
Hypergraphs naturally represent group interactions, which are omnipresen...
Hypergraphs provide a natural way of representing group relations, whose...
Influence maximization (IM) is one of the most important problems in soc...
Given a stream of graph edges from a dynamic graph, how can we assign an...
Given a web-scale graph that grows over time, how should its edges be st...
How can we detect fraudulent lockstep behavior in large-scale multi-aspe...
If we cannot store all edges in a graph stream, which edges should we st...
Consider a stream of retweet events - how can we spot fraudulent lock-st...
We consider goods that can be shared with k-hop neighbors (i.e., the set...