Substructure Aware Graph Neural Networks

SSR-DTA: Substructure-aware multi-layer graph neural networks for ...

Article on SSR-DTA: Substructure-aware multi-layer graph neural networks for drug–target binding affinity prediction, published in ...

SAME: Uncovering GNN Black Box with Structure-aware Shapley ...

Post-hoc explanation techniques on graph neural networks (GNNs) provide ... graph properties by optimizing the combination of distinct single substructures.

Adaptive aNd Structure-Aware Sampling on Graph NEuraL Networks

We propose an adaptive and structure-aware graph sampling scheme GraphANGEL for GNNs. However, it is quite challenging because both the suitable range of ...

Dual-discriminative Graph Neural Network for Imbalanced Graph ...

Specifically, an anomalous graph attribute-aware graph convolution and an anomalous graph substructure-aware deep Random Walk Kernel (deep RWK) are welded ...

Affinity-Aware Graph Networks - NIPS papers

signed for learning on molecular graphs, while the latter incorporates graph substructures. ... Position-aware graph neural networks. In Interna- tional ...

Exploiting Mutual Information for Substructure-aware Graph ...

orate with well-studied Graph Convolutional Network (GCN) techniques for learning node representations. Fortunately, re- cent studies on neural MI estimation [ ...

STNN-DDI: a Substructure-aware Tensor Neural Network to predict ...

Abstract Computational prediction of multiple-type drug–drug interaction (DDI) helps reduce unexpected side effects in poly-drug treatments.

Mathematical Expressiveness of Graph Neural Networks - ProQuest

... graph neural networks by implementing node identification and substructure awareness. Additionally, we present a comparison of existing architectures in ...

Ali Madani on LinkedIn: #neuralnetwork #drugdiscovery ...

Here is a new interesting paper titled "Substructure Aware Graph Neural Networks" The authors proposed a new #neuralnetwork framework called ...

Spatial Heterophily Aware Graph Neural Networks - Jingbo Zhou

To this end, we propose a novel Spatial Heterophily Aware Graph. Neural Network (SHGNN), to tackle the spatial heterophily on urban graphs, with two specially ...

Improving Graph Neural Network Expressivity via Subgraph ... - Stork

To this end, we propose "Graph Substructure Networks" (GSN), a topologically-aware message passing scheme based on substructure encoding. We theoretically ...

Sequence-Aware Graph Neural Network Incorporating ...

We propose sequence-aware graph neural network incorporating neighborhood information, named SAN-GNN. We construct a session graph and a neighborhood graph to ...

GSAPool: Gated Structure Aware Pooling for Graph Representation ...

Graph Neural Networks (GNNs) are powerful tools for modeling graph-structured data to solve the tasks such as node classification, link prediction along ...

Enhancing property and activity prediction and interpretation using ...

... Graph Neural Networks for Molecular Property Prediction with Substructure Masking. ... Substructure-Aware Graph Neural Network. Chem. Sci. 13, ...

Enhanced Sub-graph Reconstruction Graph Neural Network for ...

In the proposed model, the information of user and item sub-graphs is merged with the network of graph collaborative filtering, which enhances effective ...

Knowledge-aware Coupled Graph Neural Network for Social ...

Figure 3: Ablation studies for different sub-modules of. KCGN framework, in terms of HR@10 and NDCG@10. Performance over Sparsity Distributions (RQ3). One key ...

Mathematical Expressiveness of Graph Neural Networks - MDPI

... graph neural networks by implementing node identification and substructure awareness. Additionally, we present a comparison of existing ...

The Power of Recursion in Graph Neural Networks for Counting ...

Can graph neural networks count substructures? arXiv preprint arXiv:2002.04025 ... Identity-aware graph neural networks. In Pro- ceedings of the AAAI ...

using substructures for provably expressive graph neural networks ...

... aware of the local graph structure, allowing for computing messages differently depending on the topological relationship between the ...

ZINC-500k Benchmark (Graph Regression) - Papers With Code

Substructure Aware Graph Neural Networks. 2023. 10. GPTrans-Nano. 0.077. Graph Propagation Transformer for Graph Representation Learning. 2023. 11. CIN. 0.079.