The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
XGNN: Towards Model-Level Explanations of Graph Neural Networks
Open accessAbstract
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 explanations. Thus, they cannot be fully trusted and used in certain application domains if GNN models cannot be explained. In this work, we propose a novel approach, known as XGNN, to interpret GNNs at the model-level. Our approach can provide high-level insights and generic understanding of how GNNs work. In particular, we propose to explain GNNs by training a graph generator so that the generated graph patterns maximize a certain prediction of the model. We formulate the graph generation as a reinforcement learning task, where for each step, the graph generator predicts how to add an edge into the current graph. The graph generator is trained via a policy gradient method based on information from the trained GNNs. In addition, we incorporate several graph rules to encourage the generated graphs to be valid. Experimental results on both synthetic and real-world datasets show that our proposed methods help understand and verify the trained GNNs. Furthermore, our experimental results indicate that the generated graphs can provide guidance on how to improve the trained GNNs.
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
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428
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
Exploring Network Structure, Dynamics, and Function Using NetworkX
Hagberg, A. A., Schult, D. A., & Swart, P. J. (2008) · Proceedings of the Python in Science Conference · doi:10.25080/tcwv9851 · Cited by 7,477 · cited 1×
“The graphs are obtained using Networkx software package [15].”
MethodNetwork motifs: simple building blocks of complex networks.
Milo, R., Shen-Orr, S., Itzkovitz, S., Kashtan, N., Chklovskii, D., & Alon, U. (2002) · Science · doi:10.1126/science.298.5594.824 · Cited by 7,368 · cited 2×
“Different motif sets can be found in graphs with different functions [1, 23], which means different motifs may di-”
BackgroundDeep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
Network motifs: theory and experimental approaches
Alon, U. (2007) · Nature Reviews Genetics · doi:10.1038/nrg2102 · Cited by 3,279
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
Yu, L., Zhang, W., Wang, J., & Yu, Y. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10804 · Cited by 2,285
SmoothGrad: removing noise by adding noise
Smilkov, D., Thorat, N., Kim, B., Viégas, F., & Wattenberg, M. (2017) · arXiv · doi:10.48550/arxiv.1706.03825 · Cited by 1,467 · cited 2×
“Common techniques in this category include gradient-based methods [31, 32, 43], visualizations of intermediate feature maps [29, 48], and occlusion-based methods [5, 9, 45].”
MethodAn End-to-End Deep Learning Architecture for Graph Classification
Zhang, M., Cui, Z., Neumann, M., & Chen, Y. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11782 · Cited by 1,461
Interpretable Explanations of Black Boxes by Meaningful Perturbation
Fong, R. C., & Vedaldi, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.371 · Cited by 1,097
Olah, C., Mordvintsev, A., & Schubert, L. (2017) · Distill · doi:10.23915/distill.00007 · Cited by 880
Debnath, A. K., Lopez de Compadre, R. L., Debnath, G., Shusterman, A. J., & Hansch, C. (1991) · Journal of Medicinal Chemistry · doi:10.1021/jm00106a046 · Cited by 868
Rationalizing Neural Predictions
Lei, T., Barzilay, R., & Jaakkola, T. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1011 · Cited by 777 · cited 1×
“According to [21, 42], the loss function for the action at at step t can be mathematically written as”
BackgroundGraphGAN: Graph Representation Learning With Generative Adversarial Nets
Wang, H., Wang, J., Wang, J., Zhao, M., Zhang, W., Zhang, F., Xie, X., & Guo, M. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11872 · Cited by 653
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
Nguyen, A., Clune, J., Bengio, Y., Dosovitskiy, A., & Yosinski, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.374 · Cited by 578
Graph Representation Learning via Hard and Channel-Wise Attention Networks
Gao, H., & Ji, S. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330897 · Cited by 57
Self-citationInterpreting Deep Models for Text Analysis via Optimization and Regularization Methods
Yuan, H., Chen, Y., Hu, X., & Ji, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33015717 · Cited by 41
Self-citation
Cited by
Explainability in Graph Neural Networks: A Taxonomic Survey
Yuan, H., Yu, H., Gui, S., & Ji, S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3204236 · Cited by 583
Self-citationNauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., Schlötterer, J., van Keulen, M., & Seifert, C. (2023) · ACM Computing Surveys · doi:10.1145/3583558 · Cited by 590
Corso, G., Stark, H., Jegelka, S., Jaakkola, T., & Barzilay, R. (2024) · Nature Reviews Methods Primers · doi:10.1038/s43586-024-00294-7 · Cited by 454
Self-Supervised Learning of Graph Neural Networks: A Unified Review
Xie, Y., Xu, Z., Zhang, J., Wang, Z., & Ji, S. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3170559 · Cited by 389
Self-citationExplainable AI Methods - A Brief Overview
Holzinger, A., Saranti, A., Molnar, C., Biecek, P., & Samek, W. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-04083-2_2 · Cited by 379
Metadata
- Authors
- Yuan, H., Tang, J., Hu, X., & Ji, S.
- Venue
- Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
- Publisher
- ACM
- Published
- 2020-08-20
- Pages
- 430-438
- OpenAlex
- W3033892090
- Cited by
- 272
- References
- 22
- FWCI
- 12.50
- Type
- conference paper
- Language
- en
- Open access
- bronze
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.