English
Related papers

Related papers: Explaining Deep Graph Networks with Molecular Coun…

200 papers

Graph neural networks have shown great ability in representation (GNNs) learning on graphs, facilitating various tasks. Despite their great performance in modeling graphs, recent works show that GNNs tend to inherit and amplify the bias…

Machine Learning · Computer Science 2023-08-22 Zhimeng Guo , Jialiang Li , Teng Xiao , Yao Ma , Suhang Wang

Complex systems are often driven by higher-order interactions among multiple units, naturally represented as hypergraphs. Understanding dependency structures within these hypergraphs is crucial for understanding and predicting the behavior…

Social and Information Networks · Computer Science 2025-05-29 John Hood , Caterina De Bacco , Aaron Schein

While deep learning has achieved great success in many fields, one common criticism about deep learning is its lack of interpretability. In most cases, the hidden units in a deep neural network do not have a clear semantic meaning or…

Genomics · Quantitative Biology 2019-06-04 Tianle Ma , Aidong Zhang

Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor information, which have achieved promising performance on many graph tasks. However, GNNs are mostly treated as black-boxes and lack human intelligible…

Machine Learning · Computer Science 2020-06-05 Hao Yuan , Jiliang Tang , Xia Hu , Shuiwang Ji

When an image classifier outputs a wrong class label, it can be helpful to see what changes in the image would lead to a correct classification. This is the aim of algorithms generating counterfactual explanations. However, there is no…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Benedikt Höltgen , Lisa Schut , Jan M. Brauner , Yarin Gal

In recent years, deep neural networks have been extensively employed in perceptual systems to learn representations endowed with invariances, aiming to emulate the invariance mechanisms observed in the human brain. However, studies in the…

Machine Learning · Computer Science 2025-10-21 Wei Xu , Xiaoyi Jiang , Lixiang Xu , Dechao Tang

Advances in machine learning have led to graph neural network-based methods for drug discovery, yielding promising results in molecular design, chemical synthesis planning, and molecular property prediction. However, current graph neural…

Quantitative Methods · Quantitative Biology 2021-07-13 Jiahua Rao , Shuangjia Zheng , Yuedong Yang

Graph neural networks have demonstrated state-of-the-art performance on knowledge graph tasks such as link prediction. However, interpreting GNN predictions remains a challenging open problem. While many GNN explainability methods have been…

Machine Learning · Computer Science 2025-06-17 Ryoji Kubo , Djellel Difallah

Semantic parses are directed acyclic graphs (DAGs), so semantic parsing should be modeled as graph prediction. But predicting graphs presents difficult technical challenges, so it is simpler and more common to predict the linearized graphs…

Computation and Language · Computer Science 2019-10-22 Federico Fancellu , Sorcha Gilroy , Adam Lopez , Mirella Lapata

It is common practice for chemists to search chemical databases based on substructures of compounds for finding molecules with desired properties. The purpose of de novo molecular generation is to generate instead of search. Existing…

Chemical Physics · Physics 2021-02-10 Ryuichiro Hataya , Hideki Nakayama , Kazuki Yoshizoe

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

Graph neural network (GNN) explainers identify the important subgraph that ensures the prediction for a given graph. Until now, almost all GNN explainers are based on association, which is prone to spurious correlations. We propose {\name},…

Machine Learning · Computer Science 2024-07-15 Arman Behnam , Binghui Wang

Recent advances in artificial intelligence have propelled the development of innovative computational materials modeling and design techniques. Generative deep learning models have been used for molecular representation, discovery, and…

Chemical Physics · Physics 2021-02-12 Navid Shervani-Tabar , Nicholas Zabaras

Complex nonlinear models such as deep neural network (DNNs) have become an important tool for image classification, speech recognition, natural language processing, and many other fields of application. These models however lack…

Machine learning (ML) models play an increasingly prevalent role in many software engineering tasks. However, because most models are now powered by opaque deep neural networks, it can be difficult for developers to understand why the model…

Software Engineering · Computer Science 2021-11-11 Jürgen Cito , Isil Dillig , Vijayaraghavan Murali , Satish Chandra

Despite the Graph Neural Networks' (GNNs) proficiency in analyzing graph data, achieving high-accuracy and interpretable predictions remains challenging. Existing GNN interpreters typically provide post-hoc explanations disjointed from…

Machine Learning · Computer Science 2024-07-26 Zhenhua Huang , Kunhao Li , Shaojie Wang , Zhaohong Jia , Wentao Zhu , Sharad Mehrotra

Graph Neural Networks (GNNs) have shown great ability in modeling graph-structured data for various domains. However, GNNs are known as black-box models that lack interpretability. Without understanding their inner working, we cannot fully…

Machine Learning · Computer Science 2022-10-06 Enyan Dai , Suhang Wang

Counterfactual explanations (CFEs) are an emerging technique under the umbrella of interpretability of machine learning (ML) models. They provide ``what if'' feedback of the form ``if an input datapoint were $x'$ instead of $x$, then an ML…

Machine Learning · Computer Science 2021-06-16 Sahil Verma , John Dickerson , Keegan Hines

Recent advances in graph convolutional networks have significantly improved the performance of chemical predictions, raising a new research question: "how do we explain the predictions of graph convolutional networks?" A possible approach…

Machine Learning · Computer Science 2018-07-06 Hirotaka Akita , Kosuke Nakago , Tomoki Komatsu , Yohei Sugawara , Shin-ichi Maeda , Yukino Baba , Hisashi Kashima

Graph Neural Networks (GNNs), which generalize the deep neural networks to graph-structured data, have achieved great success in modeling graphs. However, as an extension of deep learning for graphs, GNNs lack explainability, which largely…

Machine Learning · Computer Science 2021-08-30 Enyan Dai , Suhang Wang