Graph Classification

Follow this topic Ask about this topic

Graph classification studies how to predict a label for an entire network, such as a molecule’s properties, a brain network’s condition, or a power grid’s failure state. Common approaches include graph kernels and handcrafted structural features, message-passing graph neural networks with pooling, and graph transformers; topological methods and language-model integrations offer additional ways to encode structure and semantics. Researchers also study explanations, uncertainty and abstention, and robustness when graph sizes, domains, or feature distributions change. A central tension is that complex learned models do not always outperform simple baselines, and performance can depend strongly on the graph domain, available attributes, and evaluation setup.

Latest papers

39 papers4 papers in the last four weeks, down 20% on the four weeks before. 0.0% of all new papers.

Path-Based Gradient Boosting for Graph-Level Prediction
Apr 26, 2026Claudio Meggio, Johan Pensar, Riccardo De BinGradient-Boosted Decision Trees Graph Representation Learning
Department of Mathematics, University of Oslo, Oslo, Norway
Subgraph Concept Networks: Concept Levels in Graph Classification
Apr 20, 2026Lucie Charlotte Magister, Alexander Norcliffe, Iulia Duta +1Graph Neural Networks Hierarchical Representation Learning
University of Cambridge Cambridge, UK
How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations
Apr 16, 2026Nouhaila Innan, Antonello Rosato, Alberto Marchisio +1Quantum Machine Learning Quantum-Inspired ML
eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD), Abu Dhabi, UAE · Department of Information Engineering, Electronics and Telecommunications, Sapienza University of Rome, Rome, Italy · Center for Quantum and Topological Systems (CQTS), NYUAD Research Institute, NYUAD, Abu Dhabi, UAE
DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation
Apr 13, 2026Yang Yan, Yunxuan Li, Qiuyan Wang +2Online Knowledge Distillation Graph Transfer Learning
School of Information Technology and Engineering, Tianjin University of Technology and Education, Tianjin, China · School of Computer Science and Technology, Tiangong University, Tianjin, China · Department of Computer Science at University of Exeter
Reservoir-Based Graph Convolutional Networks
Mar 25, 2026Mayssa Soussia, Gita Ayu Salsabila, Mohamed Ali Mahjoub +1Graph Neural Networks Convolutional Neural Networks
National Engineering School of Sousse, University of Sousse, LATIS – Laboratory of Advanced Technology and Intelligent Systems, 4023, Sousse, Tunisia. · BASIRA Lab, Imperial-X and Department of Computing, Imperial College London, London, UK.
SketchGraphNet: A Memory-Efficient Hybrid Graph Transformer for Large-Scale Sketch Corpora Recognition
Mar 8, 2026Shilong Chen, Mingyuan Li, Zhaoyang Wang +2Memory-Efficient Attention Graph Transformer
College of Computer, Qinghai Normal University, Xining, 810001, Qinghai, China · College of Computer, Nanjing University, Nanjing, 210023, Jiangsu, China · College of Computer, Qinghai Minzu University, Xining, 810007, Qinghai, China
Feature-based morphological analysis of shape graph data
Feb 18, 2026Murad Hossen, Demetrio Labate, Nicolas CharonGraph Classification Statistical Shape Modeling
Department of Mathematics, University of Houston, Houston, Texas, USA.
Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark
Aug 8, 2025Ngoc N. Tran, Anwar Said, Waseem Abbas +2Distribution Shift Robustness Graph Representation Learning
Vanderbilt University, USA · Highmark Health, USA · University of Texas at Dallas, USA
Heterogeneous Sheaf Neural Networks
Sep 12, 2024Luke Braithwaite, Alessio Borgi, Gabriele Onorato +4Heterogeneous GNNs Sheaf Neural Networks
Department of Computer Science and Technology, University of Cambridge · Department of Computer, Control and Management Engineering, Sapienza University of Rome · Department of Electrical and Computer Engineering, Northeastern University

Apr 26, 2026J/K move · Enter open · S save

Path-Based Gradient Boosting for Graph-Level Prediction

Claudio Meggio, Johan Pensar, Riccardo De Bin

Department of Mathematics, University of Oslo, Oslo, Norway

Gradient-Boosted Decision Trees Graph Representation Learning Graph Classification

Open paper AskPDF arXiv

We propose PathBoost, a gradient tree boosting method for graph-level classification and regression that learns discriminative path-based features directly from the input graph structure. Building on a previous work, which was tailored to a specific chemistry application, PathBoost introduces three key extensions: (i) adaptation to binary classification through gradient boosting with a logistic loss, (ii) incorporation of multiple node and edge attributes into the path feature space via a prefix-based decomposition, and (iii) automatic anchor node selection based on categorical attribute diversity, eliminating the need for the user to specify the starting point of the considered path features. We compared PathBoost to graph neural networks and graph kernel approaches on several benchmark datasets, obtaining better results in half of them, and comparable results in the rest. PathBoost shows better performances on graphs with larger average node counts. Overall, the results demonstrate that path-based boosting methods can be competitive with more complex black-box approaches.