We present GERN, a novel scalable framework for training GNNs in node classification tasks, based on effective resistance, a standard tool in spectral graph theory. Our method progressively refines the GNN weights on a sequence of random spanning trees suitably transformed into path graphs which, despite their simplicity, are shown to retain essential topological and node information of the original input graph. The sparse nature of these path graphs substantially lightens the computational burden of GNN training. This not only enhances scalability but also improves accuracy in subsequent test phases, especially under small training set regimes, which are of great practical importance, as in many real-world scenarios labels may be hard to obtain. In these settings, our framework yields very good results as it effectively counters the training deterioration caused by overfitting when the training set is small. Our method also addresses common issues like over-squashing and over-smoothing while avoiding under-reaching phenomena.
Although our framework is flexible and can be deployed in several types of GNNs, in this paper we focus on graph convolutional networks and carry out an extensive experimental investigation on a number of real-world graph benchmarks, where we achieve simultaneous improvement of training speed and test accuracy over a wide pool of representative baselines.
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs
Institute of Artificial Intelligence Innovation and Industry, Fudan University(复旦大学人工智能创新与产业研究院);Shanghai Academy of AI for Science(上海人工智能科学研究院);Human Phenome Institute, Fudan University(复旦大学人类表型组研究院);School of Information and Communication Engineering, Communication University of China(中国传媒大学信息与通信工程学院)
HAGNN: Hybrid Aggregation for Heterogeneous Graph Neural Networks
State Key Laboratory for Novel Software Technology, Nanjing University(南京大学现代软件技术国家重点实验室);Research Center for Graph Computing, Zhejiang Lab(浙江实验室图计算研究中心)
Customizing Graph Neural Networks using Path Reweighting
Virginia Tech(弗吉尼亚理工大学);Peking University(北京大学);Carnegie Mellon University(卡内基梅隆大学);Shanghai Jiao Tong University(上海交通大学);University of Electronic Science and Technology of China(电子科技大学);Norwegian University of Science and Technology(挪威科技大学)
What Functions Can Graph Neural Networks Generate?
University of Pennsylvania(宾夕法尼亚大学);Yale University(耶鲁大学)
In this paper, we fully answer the above question through a key algebraic condition on graph functions, called \textit{permutation compatibility} , that relates permutations of weights and features of the graph to functional constraints. We prove that: (i) a GNN, as a graph function, is necessarily permutation compatible; (ii) conversely, any permutation compatible function, when restricted on input graphs with distinct node features, can be generated by a GNN; (iii) for arbitrary node features (not necessarily distinct), a simple feature augmentation scheme suffices to generate a permutation …
GNN-based Path-aware multi-view Circuit Learning for Technology Mapping
Faculty of Electrical Engineering and Computer Science, NingBo University(电子工程与计算机科学学院,宁波大学);University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University(密歇根大学-上海交通大学联合研究所,上海交通大学);Department of Computer Science and Engineering, The Chinese University of Hong Kong(中国香港中文大学计算机科学与工程系)
Robust and Fast Data-Driven Power System State Estimator Using Graph Neural Networks
The Institute for Artificial Intelligence Research and Development of Serbia(塞尔维亚人工智能研发研究所);Faculty of Electrical Engineering, University of Sarajevo(萨拉热窝大学电气工程学院);Faculty of Technical Sciences, University of Novi Sad(诺维萨德大学技术科学学院)
Feature Correlation Aggregation: on the Path to Better Graph Neural Networks
Australian National University(澳大利亚国立大学);École polytechnique fédérale de Lausanne(洛桑联邦理工学院);Data61, CSIRO(澳大利亚联邦科学与工业研究组织数据61);Monash University(莫纳什大学)
An Efficient Subgraph GNN with Provable Substructure Counting Power
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Beijing Institute for General Artificial Intelligence(北京通用人工智能研究院)
FastGL: A GPU-Efficient Framework for Accelerating Sampling-Based GNN Training at Large Scale
Institute of Automation, CAS(中国科学院自动化研究所);School of Future Technology, University of Chinese Academy of Sciences(中国科学院大学未来技术学院);Shanghai Jiao Tong University(上海交通大学);AiRiA
Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embedding
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);School of Artificial Intelligence, Hebei University of Technology(河北工业大学人工智能学院)
GRecX: An Efficient and Unified Benchmark for GNN-based Recommendation
Hefei University of Technology(合肥工业大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)
GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning
Centre for Pattern Analysis and Machine Intelligence, Department of Electrical and Computer Engineering, University of Waterloo(模式分析与机器智能中心,电气与计算机工程系,滑铁库大学);Machine Learning Department at Mohamed bin Zayed University of Artificial Intelligence(人工智能穆罕默德·本·扎耶德大学机器学习系)
Highly Accurate Disease Diagnosis and Highly Reproducible Biomarker Identification with PathFormer
Washington University in St. Louis(圣路易斯华盛顿大学);The Hong Kong Polytechnic University(香港理工大学);Institute for Informatics (I2)(信息学研究所(I2));Peking University(北京大学);Washington University School of Medicine(华盛顿大学医学院)