Can graph neural networks count substructures?
The ability to detect and count certain substructures in graphs is important for solving many
tasks on graph-structured data, especially in the contexts of computational chemistry and …
tasks on graph-structured data, especially in the contexts of computational chemistry and …
Boosting the Cycle Counting Power of Graph Neural Networks with I-GNNs
Message Passing Neural Networks (MPNNs) are a widely used class of Graph Neural
Networks (GNNs). The limited representational power of MPNNs inspires the study of …
Networks (GNNs). The limited representational power of MPNNs inspires the study of …
Distance-restricted folklore weisfeiler-leman GNNs with provable cycle counting power
The ability of graph neural networks (GNNs) to count certain graph substructures, especially
cycles, is important for the success of GNNs on a wide range of tasks. It has been recently …
cycles, is important for the success of GNNs on a wide range of tasks. It has been recently …
Are more layers beneficial to graph transformers?
Despite that going deep has proven successful in many neural architectures, the existing
graph transformers are relatively shallow. In this work, we explore whether more layers are …
graph transformers are relatively shallow. In this work, we explore whether more layers are …
Mining weighted subgraphs in a single large graph
Weighted single large graphs are often used to simulate complex systems, and thus mining
frequent subgraphs in a weighted large graph is an important issue that has attracted the …
frequent subgraphs in a weighted large graph is an important issue that has attracted the …
Efficiently counting substructures by subgraph gnns without running gnn on subgraphs
Using graph neural networks (GNNs) to approximate specific functions such as counting
graph substructures is a recent trend in graph learning. Among these works, a popular way …
graph substructures is a recent trend in graph learning. Among these works, a popular way …
Two-level graph neural network
Graph neural networks (GNNs) are recently proposed neural network structures for the
processing of graph-structured data. Due to their employed neighbor aggregation strategy …
processing of graph-structured data. Due to their employed neighbor aggregation strategy …
Expressivity of graph neural networks through the lens of adversarial robustness
We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that
are provably more powerful than traditional Message Passing Neural Networks (MPNNs). In …
are provably more powerful than traditional Message Passing Neural Networks (MPNNs). In …
Boosting Graph Pooling with Persistent Homology
Recently, there has been an emerging trend to integrate persistent homology (PH) into
graph neural networks (GNNs) to enrich expressive power. However, naively plugging PH …
graph neural networks (GNNs) to enrich expressive power. However, naively plugging PH …
HUSM: High utility subgraph mining in single graph databases
Z Chen, C He, G Chen, W Gan, P Fournier-Viger - Information Sciences, 2024 - Elsevier
Frequent subgraph mining (FSM) is a crucial research area with diverse applications.
However, traditional FSM treats all subgraphs as equally important. In practical applications …
However, traditional FSM treats all subgraphs as equally important. In practical applications …