Machine learning on graphs: A model and comprehensive taxonomy
There has been a surge of recent interest in graph representation learning (GRL). GRL
methods have generally fallen into three main categories, based on the availability of …
methods have generally fallen into three main categories, based on the availability of …
State of the art and potentialities of graph-level learning
Graphs have a superior ability to represent relational data, such as chemical compounds,
proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as …
proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as …
[PDF][PDF] Survey on graph embeddings and their applications to machine learning problems on graphs
Dealing with relational data always required significant computational resources, domain
expertise and task-dependent feature engineering to incorporate structural information into a …
expertise and task-dependent feature engineering to incorporate structural information into a …
A large-scale database for graph representation learning
With the rapid emergence of graph representation learning, the construction of new large-
scale datasets is necessary to distinguish model capabilities and accurately assess the …
scale datasets is necessary to distinguish model capabilities and accurately assess the …
[HTML][HTML] Generic network sparsification via degree-and subgraph-based edge sampling
Network (or graph) sparsification accelerates many downstream analyses. For graph
sparsification, sampling methods derived from local heuristic considerations are common in …
sparsification, sampling methods derived from local heuristic considerations are common in …
Moomin: Deep molecular omics network for anti-cancer drug combination therapy
We propose the molecular omics network (MOOMIN) a multimodal graph neural network
used by AstraZeneca oncologists to predict the synergy of drug combinations for cancer …
used by AstraZeneca oncologists to predict the synergy of drug combinations for cancer …
On the similarity between von Neumann graph entropy and structural information: Interpretation, computation, and applications
X Liu, L Fu, X Wang, C Zhou - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The von Neumann graph entropy is a measure of graph complexity based on the Laplacian
spectrum. It has recently found applications in various learning tasks driven by the …
spectrum. It has recently found applications in various learning tasks driven by the …
A comparison of graph neural networks for malware classification
Managing the threat posed by malware requires accurate detection and classification
techniques. Traditional detection strategies, such as signature scanning, rely on manual …
techniques. Traditional detection strategies, such as signature scanning, rely on manual …
Video source characterization using encoding and encapsulation characteristics
We introduce the use of video coding settings for source identification and propose a new
approach that incorporates encoding and encapsulation aspects of a video. To this end, a …
approach that incorporates encoding and encapsulation aspects of a video. To this end, a …
[HTML][HTML] Generic network sparsification via hybrid edge sampling
Network (or graph) sparsification benefits downstream graph mining tasks. Finding a
sparsified subgraph G ˆ similar to the original graph G is, however, challenging due to the …
sparsified subgraph G ˆ similar to the original graph G is, however, challenging due to the …