Extract the knowledge of graph neural networks and go beyond it: An effective knowledge distillation framework
Semi-supervised learning on graphs is an important problem in the machine learning area.
In recent years, state-of-the-art classification methods based on graph neural networks …
In recent years, state-of-the-art classification methods based on graph neural networks …
Is a single embedding enough? learning node representations that capture multiple social contexts
Recent interest in graph embedding methods has focused on learning a single
representation for each node in the graph. But can nodes really be best described by a …
representation for each node in the graph. But can nodes really be best described by a …
A unified framework for community detection and network representation learning
Network representation learning (NRL) aims to learn low-dimensional vectors for vertices in
a network. Most existing NRL methods focus on learning representations from local context …
a network. Most existing NRL methods focus on learning representations from local context …
Semantic proximity search on graphs with metagraph-based learning
Given ubiquitous graph data such as the Web and social networks, proximity search on
graphs has been an active research topic. The task boils down to measuring the proximity …
graphs has been an active research topic. The task boils down to measuring the proximity …
Ego-splitting framework: From non-overlapping to overlapping clusters
We propose ego-splitting, a new framework for detecting clusters in complex networks which
leverage the local structures known as ego-nets (ie the subgraph induced by the …
leverage the local structures known as ego-nets (ie the subgraph induced by the …
Meta-inductive node classification across graphs
Semi-supervised node classification on graphs is an important research problem, with many
real-world applications in information retrieval such as content classification on a social …
real-world applications in information retrieval such as content classification on a social …
mg2vec: Learning relationship-preserving heterogeneous graph representations via metagraph embedding
Given that heterogeneous information networks (HIN) encompass nodes and edges
belonging to different semantic types, they can model complex data in real-world scenarios …
belonging to different semantic types, they can model complex data in real-world scenarios …
Semantic proximity search on heterogeneous graph by proximity embedding
Many real-world networks have a rich collection of objects. The semantics of these objects
allows us to capture different classes of proximities, thus enabling an important task of …
allows us to capture different classes of proximities, thus enabling an important task of …
Ego-net community mining applied to friend suggestion
In this paper, we present a study of the community structure of ego-networks---the graphs
representing the connections among the neighbors of a node---for several online social …
representing the connections among the neighbors of a node---for several online social …
Discovering communities and anomalies in attributed graphs: Interactive visual exploration and summarization
Given a network with node attributes, how can we identify communities and spot anomalies?
How can we characterize, describe, or summarize the network in a succinct way …
How can we characterize, describe, or summarize the network in a succinct way …