Graph Neural Networks with Heterophily
Open accessThe DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Abstract
Graph Neural Networks (GNNs) have proven to be useful for many different practical applications. However, many existing GNN models have implicitly assumed homophily among the nodes connected in the graph, and therefore have largely overlooked the important setting of heterophily, where most connected nodes are from different classes. In this work, we propose a novel framework called CPGNN that generalizes GNNs for graphs with either homophily or heterophily. The proposed framework incorporates an interpretable compatibility matrix for modeling the heterophily or homophily level in the graph, which can be learned in an end-to-end fashion, enabling it to go beyond the assumption of strong homophily. Theoretically, we show that replacing the compatibility matrix in our framework with the identity (which represents pure homophily) reduces to GCN. Our extensive experiments demonstrate the effectiveness of our approach in more realistic and challenging experimental settings with significantly less training data compared to previous works: CPGNN variants achieve state-of-the-art results in heterophily settings with or without contextual node features, while maintaining comparable performance in homophily settings.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Emergence of Scaling in Random Networks
Barabási, A.-L., & Albert, R. (1999) · Science · doi:10.1126/science.286.5439.509 · Cited by 36,135
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853
Birds of a Feather: Homophily in Social Networks
McPherson, M., Smith-Lovin, L., & Cook, J. M. (2001) · Annual Review of Sociology · doi:10.1146/annurev.soc.27.1.415 · Cited by 18,567
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1710.10903 · Cited by 12,107
Inductive Representation Learning on Large Graphs
Hamilton, W. L., Ying, R., & Leskovec, J. (2017) · arXiv · doi:10.48550/arxiv.1706.02216 · Cited by 10,639
The graph neural network model
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2008.2005605 · Cited by 9,582
Veličković, P., Casanova, A., Liò, P., Cucurull, G., Romero, A., & Bengio, Y. (2017) · arXiv (Cornell University) · doi:10.17863/cam.48429 · Cited by 8,657
Targeted Branching for the Maximum Independent Set Problem Using Graph Neural Networks
Silva, G., Rodrigues, M., Teixeira, A., & Amorim, M. (2024) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.sea.2024.20 · Cited by 5,183
Advances In Deep Learning On Graphs (Gsp'18 Workshop)
Defferrard, M. (2016) · Figshare · doi:10.5281/zenodo.1286817 · Cited by 4,613
Graph Convolutional Neural Networks for Web-Scale Recommender Systems
Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W. L., & Leskovec, J. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3219890 · Cited by 3,733
Collective Classification in Network Data
Sen, P., Namata, G., Bilgic, M., Getoor, L., Gallagher, B., & Eliassi‐Rad, T. (2008) · AI Magazine · doi:10.1609/aimag.v29i3.2157 · Cited by 3,293
The Network Data Repository with Interactive Graph Analytics and Visualization
Rossi, R., & Ahmed, N. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9277 · Cited by 2,412
Self-citationSimple and Deep Graph Convolutional NetworksPreprint
Chen, M., Wei, Z., Huang, Z., Ding, B., & Li, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02133 · Cited by 1,731
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Defferrard, M., Bresson, X., & Vandergheynst, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.09375 · Cited by 1,673
Understanding belief propagation and its generalizations
Yedidia, J. S., Freeman, W. T., & Weiss, Y. (2003) · Cited by 1,594
Modeling polypharmacy side effects with graph convolutional networks
Zitnik, M., Agrawal, M., & Leskovec, J. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty294 · Cited by 1,501
DeepGCNs: Can GCNs Go As Deep As CNNs?
Li, G., Muller, M., Thabet, A., & Ghanem, B. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00936 · Cited by 1,400
Simplifying Graph Convolutional Networks
Wu, F., Zhang, T., Junior, A. H. D. S., Fifty, C., Yu, T., & Weinberger, K. Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.07153 · Cited by 1,165
Representation Learning on Graphs with Jumping Knowledge Networks
Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K., & Jegelka, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03536 · Cited by 891
Concerning nonnegative matrices and doubly stochastic matrices
Sinkhorn, R., & Knopp, P. (1967) · Pacific Journal of Mathematics · doi:10.2140/pjm.1967.21.343 · Cited by 887
Multi-Scale attributed node embedding
Rozemberczki, B., Allen, C., & Sarkar, R. (2021) · Journal of Complex Networks · doi:10.1093/comnet/cnab014 · Cited by 640
Getoor, L. (2006) · Advanced Information and Knowledge Processing · doi:10.1007/1-84628-284-5_7 · Cited by 612
Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
Dou, Y., Liu, Z., Sun, L., Deng, Y., Peng, H., & Yu, P. S. (2020) · Proceedings of the 29th ACM International Conference on Information & Knowledge Management · doi:10.1145/3340531.3411903 · Cited by 612
DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
Rong, Y., Huang, W., Xu, T., & Huang, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.10903 · Cited by 607
Query-driven active surveying for collective classification
Namata, G. M. S., London, B., Getoor, L. C., & Huang, B. (2012) · Mining and Learning with Graphs · Cited by 590
Protein interface prediction using graph convolutional networks
Fout, A., Ben‐Hur, A., Anderson, C., Chitsaz, H., & Zhou, W. (2017) · Digital Collections of Colorado (Colorado State University) · doi:10.25675/3.021826 · Cited by 513
Geom-GCN: Geometric Graph Convolutional Networks
Pei, H., Wei, B., Chang, K. C., Yu, L., & Yang, B. X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.05287 · Cited by 396
Netprobe: a fast and scalable system for fraud detection in online auction networks
Pandit, S., Chau, D. H., Wang, S., & Faloutsos, C. (2007) · Proceedings of the 16th international conference on World Wide Web · doi:10.1145/1242572.1242600 · Cited by 382
Iterative Classification in Relational Data
Neville, J., & Jensen, D. D. (2000) · Cited by 318
Homophily influences ranking of minorities in social networks
Karimi, F., Génois, M., Wagner, C., Singer, P., & Strohmaier, M. (2018) · Scientific Reports · doi:10.1038/s41598-018-29405-7 · Cited by 272
Revisiting Semi-Supervised Learning with Graph Embeddings
Yang, Z., Cohen, W. W., & Salakhutdinov, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.08861 · Cited by 263
DeeperGCN: All You Need to Train Deeper GCNs
Li, G., Xiong, C., Thabet, A., & Ghanem, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.07739 · Cited by 239
Attention-based Graph Neural Network for Semi-supervised Learning
Thekumparampil, K. K., Wang, C., Oh, S., & Li, L.-J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.03735 · Cited by 235
GMNN: Graph Markov Neural NetworksPreprint
Qu, M., Bengio, Y., & Tang, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.06214 · Cited by 232
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Zhu, J., Yan, Y., Zhao, L., Heimann, M., Akoglu, L., & Koutra, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.11468 · Cited by 169
Self-citationTwo Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
Yan, Y., Hashemi, M., Swersky, K., Yang, Y., & Koutra, D. (2022) · 2022 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm54844.2022.00169 · Cited by 165
Self-citationHomophily influences ranking of minorities in social networks
Karimi, F., Génois, M., Wagner, C., Singer, P., & Strohmaier, M. (2018) · RWTH Publications (RWTH Aachen) · Cited by 145
Unifying Guilt-by-Association Approaches: Theorems and Fast Algorithms
Koutra, D., Ke, T.-Y., Kang, U., Chau, D. H., Pao, H.-K., & Faloutsos, C. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23783-6_16 · Cited by 123
Self-citationTransforming Graph Data for Statistical Relational Learning
Rossi, R. A., McDowell, L. K., Aha, D. W., & Neville, J. (2012) · Journal of Artificial Intelligence Research · doi:10.1613/jair.3659 · Cited by 82
Self-citationYan, Y., Zhu, J., Duda, M., Solarz, E., Sripada, C., & Koutra, D. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330921 · Cited by 80
Self-citationLearning Role-based Graph EmbeddingsPreprint
Ahmed, N. K., Rossi, R. A., Lee, J. B., Willke, T. L., Zhou, R., Kong, X., & Eldardiry, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.02896 · Cited by 76
Self-citationGraph Agreement Models for Semi-Supervised Learning
Stretcu, O., Viswanathan, K., Movshovitz‐Attias, D., Platanios, E. A., Ravi, S., & Tomkins, A. (2019) · neural information processing systems · Cited by 75
Alhajj, R., & Rokne, J. G. (2014) · Springer eBooks · doi:10.1007/978-1-4614-6170-8_100636 · Cited by 72
Cautious Inference in Collective Classification
McDowell, L. K., Gupta, K. M., & Aha, D. W. (2007) · Defense Technical Information Center (DTIC) · doi:10.21236/ada479429 · Cited by 67
Linearized and single-pass belief propagation
Gatterbauer, W., Günnemann, S., Koutra, D., & Faloutsos, C. (2015) · Proceedings of the VLDB Endowment · doi:10.14778/2735479.2735490 · Cited by 63
Self-citationNetProbe: A Fast and Scalable System for Fraud Detection in Online Auction Networks
Pandit, S., Chau, D. H., Wang, S., & Faloutsos, C. (2018) · KiltHub Repository · doi:10.1184/r1/6607661 · Cited by 32
Relational Similarity Machines (RSM): A Similarity-based Learning Framework for Graphs
Rossi, R. A., Zhou, R., Ahmed, N. K., & Eldardiry, H. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622638 · Cited by 7
Self-citationChen, T., Wang, Z., Li, L., Li, D., Li, Z., Chang, X., Bian, P., Liang, G., Wang, Q., & Xie, T. (2025) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.ecoop.2025.6
Cited by
Shao, Z., Wang, F., Xu, Y., Wei, W., Yu, C., Zhang, Z., Yao, D., Sun, T., Jin, G., Cao, X., et al. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3484454 · Cited by 190
Metadata
- Authors
- Zhu, J., Rossi, R. A., Rao, A., Mai, T., Lipka, N., Ahmed, N. K., & Koutra, D.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2021-05-18
- Volume
- 35
- Issue
- 12
- Pages
- 11168-11176
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W3090999459
- Cited by
- 224
- References
- 48
- FWCI
- 18.76
- Type
- conference paper
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.