HyperGCN – a multi-layer multi-exit graph neural network to enhance hyperspectral image classification

References

• Achanta, R., A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Süsstrunk. 2012. “SLIC Superpixels Compared to State-of-The-Art Superpixel Methods.” IEEE Transactions on Pattern Analysis & Machine Intelligence 34 (11): 2274–2282. https://doi.org/10.1109/TPAMI.2012.120.
   PubMed Web of Science ®Google Scholar
• Bronstein, M. M., J. Bruna, Y. LeCun, A. Szlam, and P. Vandergheynst. 2017. “Geometric Deep Learning: Going Beyond Euclidean Data.” IEEE Signal Processing Magazine 34 (4): 18–42. https://doi.org/10.1109/MSP.2017.2693418.
   Web of Science ®Google Scholar
• Chen, M., Z. Wei, Z. Huang, B. Ding, and Y. Li. 2020. “Simple and Deep Graph Convolutional Networks.” International Conference on Machine Learning, Originally scheduled in Vienna, Austria, held virtually, 1725–1735. PMLR.
   Google Scholar
• Chen, Y., H. Jiang, C. Li, X. Jia, and P. Ghamisi. 2016. “Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks.” IEEE Transactions on Geoscience & Remote Sensing 54 (10): 6232–6251. https://doi.org/10.1109/TGRS.2016.2584107.
   Web of Science ®Google Scholar
• Chen, Y., Z. Lin, X. Zhao, G. Wang, and Y. Gu. 2014. “Deep Learning-Based Classification of Hyperspectral Data.” IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing 7 (6): 2094–2107. https://doi.org/10.1109/JSTARS.2014.2329330.
   Web of Science ®Google Scholar
• Gasteiger, J., A. Bojchevski, and S. Günnemann. 2019. “Predict Then Propagate: Graph Neural Networks Meet Personalized Pagerank.” The 7th International Conference on Learning Representations (ICLR 2019), New Orleans, LA, USA. https://doi.org/10.48550/arXiv.1810.05997
   Google Scholar
• Gilmer, J., S. S. Schoenholz, P. F. Riley, O. Vinyals, and G. E. Dahl. 2017. “Neural Message Passing for Quantum Chemistry.” International conference on machine learning, Sydney, Australia, 1263–1272. PMLR.
   Google Scholar
• Gori, M., G. Monfardini, and F. Scarselli. 2005. “A New Model for Learning in Graph Domains.” In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, Montreal, QC, Canada, 729–734.
   Google Scholar
• Hamilton, W. L., R. Ying, and J. Leskovec. 2017. “Inductive Representation Learning on Large Graphs.” The 31st International Conference on Neural Information Processing Systems (NIPS’17), Red Hook, NY, USA, 1025–1035. Curran Associates Inc.
   Google Scholar
• Hammond, D. K., P. Vandergheynst, and R. Gribonval. 2011. “Wavelets on Graphs via Spectral Graph Theory.” Applied and Computational Harmonic Analysis 30 (2): 129–150. https://doi.org/10.1016/j.acha.2010.04.005.
   Web of Science ®Google Scholar
• Hang, R., F. Zhou, Q. Liu, and P. Ghamisi. 2020. “Classification of Hyperspectral Images via Multitask Generative Adversarial Networks.” IEEE Transactions on Geoscience & Remote Sensing 59 (2): 1424–1436. https://doi.org/10.1109/TGRS.2020.3003341.
   Web of Science ®Google Scholar
• Harsanyi, J. C., and C.-I. Chang. 1994. “Hyperspectral Image Classification and Dimensionality Reduction: An Orthogonal Subspace Projection Approach.” IEEE Transactions on Geoscience & Remote Sensing 32 (4): 779–785. https://doi.org/10.1109/36.298007.
   Web of Science ®Google Scholar
• Haseena Rahmath, P., V. Srivastava, and K. Chaurasia. 2023. “A Strategy to Accelerate the Inference of a Complex Deep Neural Network.” In Proceedings of Data Analytics and Management: ICDAM 2022, Virtual conference, 57–68. Springer.
   Google Scholar
• Hong, D., L. Gao, J. Yao, B. Zhang, A. Plaza, and J. Chanussot. 2020. “Graph Convolutional Networks for Hyperspectral Image Classification.” IEEE Transactions on Geoscience & Remote Sensing 59 (7): 5966–5978. https://doi.org/10.1109/TGRS.2020.3015157.
   Web of Science ®Google Scholar
• Hong, D., N. Yokoya, J. Chanussot, and X. Xiang Zhu. 2019. “CoSpace: Common Subspace Learning from Hyperspectral-Multispectral Correspondences.” IEEE Transactions on Geoscience & Remote Sensing 57 (7): 4349–4359. https://doi.org/10.1109/TGRS.2018.2890705.
   Web of Science ®Google Scholar
• Huang, K., S. Li, X. Kang, and L. Fang. 2016. “Spectral–Spatial Hyperspectral Image Classification Based on KNN.” Sensing and Imaging 17 (1): 1–13. https://doi.org/10.1007/s11220-015-0126-z.
   Google Scholar
• Hwang, H., S. Lee, C. Park, and K. Shin. 2022. “AHP: Learning to Negative Sample for Hyperedge Prediction.” The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2022), Madrid, Spain, 2237–2242. https://doi.org/10.1145/3477495.3531836.
   Google Scholar
• Jia, S., S. Jiang, S. Zhang, M. Xu, and X. Jia. 2024. “Graph-In-Graph Convolutional Network for Hyperspectral Image Classification.” IEEE Transactions on Neural Networks and Learning Systems 35:1157–1171. https://doi.org/10.1109/TNNLS.2022.3182715.
   Web of Science ®Google Scholar
• Kaya, Y., S. Hong, and T. Dumitras. 2019. “Shallow-Deep Networks: Understanding and Mitigating Network Overthinking.” International conference on machine learning (ICML-2019), Long Beach, California, USA, 3301–3310. PMLR.
   Google Scholar
• Khodadadzadeh, M., J. Li, A. Plaza, and J. M. Bioucas-Dias. 2014. “A Subspace-Based Multinomial Logistic Regression for Hyperspectral Image Classification.” IEEE Geoscience & Remote Sensing Letters 11 (12): 2105–2109. https://doi.org/10.1109/LGRS.2014.2320258.
   Web of Science ®Google Scholar
• Kipf, T. N., and M. Welling. 2017. “Semi-Supervised Classification with Graph Convolutional Networks.” The 5th International Conference on Learning Representations (ICLR 2017), Toulon, France. https://doi.org/10.48550/arXiv.1609.02907.
   Google Scholar
• Kraemer, H. C. 2015. “Kappa Coefficient.” Wiley StatsRef: Statistics Reference Online, edited by N. Balakrishnan, T. Colton, and B. Everitt, 1–4. Hoboken, NJ, USA: Wiley.
   Google Scholar
• Landgrebe, D. 2002. “Hyperspectral Image Data Analysis.” IEEE Signal Processing Magazine 19 (1): 17–28. https://doi.org/10.1109/79.974718.
   Web of Science ®Google Scholar
• Li, G., M. Muller, A. Thabet, and B. Ghanem. 2019. “Deepgcns: Can Gcns Go As Deep As Cnns?” Proceedings of the IEEE/CVF international conference on computer vision, Seoul, Korea, 9267–9276.
   Google Scholar
• Li, Q., Z. Han, and X.-M. Wu. 2018. “Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning.” In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th Innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018, edited by S. A. McIlraith and K. Q. Weinberger, 3538–3545. New Orleans, Louisiana, USA: AAAI Press.
   Google Scholar
• Li, Y., D. Tarlow, M. Brockschmidt, and R. Zemel. 2016. “Gated Graph Sequence Neural Networks.” The 4th International Conference on Learning Representations (ICLR 2016), San Juan, Puerto Rico. https://doi.org/10.48550/arXiv.1511.05493.
   Google Scholar
• Liu, Q., L. Xiao, J. Yang, and Z. Wei. 2021. “CNN-Enhanced Graph Convolutional Network with Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification.” IEEE Transactions on Geoscience & Remote Sensing 59 (10): 8657–8671. https://doi.org/10.1109/TGRS.2020.3037361.
   Web of Science ®Google Scholar
• Liu, Q., F. Zhou, R. Hang, and X. Yuan. 2017. “Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification.” Remote Sensing 9 (12): 1330. https://doi.org/10.3390/rs9121330.
   Web of Science ®Google Scholar
• Marion, F., L. B. L. Baumgardner, and A. Landgrebe David. 2015. “220 Band AVIRIS Hyperspectral Image Data Set: June 12, 1992 Indian Pine Test Site 3.” https://purr.purdue.edu/publications/1947/1.
   Google Scholar
• Melgani, F., and L. Bruzzone. 2004. “Classification of Hyperspectral Remote Sensing Images with Support Vector Machines.” IEEE Transactions on Geoscience & Remote Sensing 42 (8): 1778–1790. https://doi.org/10.1109/TGRS.2004.831865.
   Web of Science ®Google Scholar
• Panda, P., A. Sengupta, and K. Roy. 2017. “Energy-Efficient and Improved Image Recognition with Conditional Deep Learning.” ACM Journal on Emerging Technologies in Computing Systems (JETC) 13 (3): 1–21. https://doi.org/10.1145/3007192.
   Web of Science ®Google Scholar
• Patel, H., and K. P. Upla. 2022. “A Shallow Network for Hyperspectral Image Classification Using an Autoencoder with Convolutional Neural Network.” Multimedia Tools & Applications 81 (1): 695–714. https://doi.org/10.1007/s11042-021-11422-w.
   Web of Science ®Google Scholar
• Pham, T., T. Tran, D. Phung, and S. Venkatesh. 2017. “Column Networks for Collective Classification.” Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI’17, San Francisco, California, USA, 2485–2491. AAAI Press.
   Google Scholar
• Qin, A., Z. Shang, J. Tian, Y. Wang, T. Zhang, and Y. Yan Tang. 2018. “Spectral–Spatial Graph Convolutional Networks for Semisupervised Hyperspectral Image Classification.” IEEE Geoscience & Remote Sensing Letters 16 (2): 241–245. https://doi.org/10.1109/LGRS.2018.2869563.
   Web of Science ®Google Scholar
• Rahimi, A., T. Cohn, and T. Baldwin. 2018. “Semi-Supervised User Geolocation via Graph Convolutional Networks.” The 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), edited by I. Gurevych and Y. Miyao, Melbourne, Australia, 2009­–2019. Association for Computational Linguistics. https://doi.org/10.18653/v1/P18-1187.
   Google Scholar
• Rong, Y., W. Huang, T. Xu, and J. Huang. 2020. “Dropedge: Towards Deep Graph Convolutional Networks on Node Classification.” International Conference on Learning Representations (ICLR 2020), Virtual Conference. https://openreview.net/pdf?id=Hkx1qkrKPr.
   Google Scholar
• Shahraki, F. F., and S. Prasad. 2018. “Graph Convolutional Neural Networks for Hyperspectral Data Classification.” In 2018 IEEE global conference on signal and information processing (GlobalSIP), Anaheim, CA, USA, 968–972. IEEE. https://doi.org/10.1109/GlobalSIP.2018.8645969.
   Google Scholar
• Tang, L., and H. Liu. 2009. “Relational Learning via Latent Social Dimensions.” In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, Paris, France, 817–826.
   Google Scholar
• Teerapittayanon, S., B. McDanel, and H.-T. Kung. 2016. “Branchynet: Fast Inference via Early Exiting from Deep Neural Networks.” In 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico, 2464–2469. IEEE.
   Google Scholar
• Ud Din, A. M., and S. Qureshi. 2024. “Limits of Depth: Over-Smoothing and Over-Squashing in GNNs.” Big Data Mining & Analytics 7 (1): 205–216. https://doi.org/10.26599/BDMA.2023.9020019.
   Google Scholar
• Veličković, P., G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio. 2018. “Graph Attention Networks.” International Conference on Learning Representations (ICLR 2018), Vancouver, Canada. https://openreview.net/pdf?id=rJXMpikCZ.
   Google Scholar
• Wan, S., C. Gong, P. Zhong, S. Pan, G. Li, and J. Yang. 2020. “Hyperspectral Image Classification with Context-Aware Dynamic Graph Convolutional Network.” IEEE Transactions on Geoscience & Remote Sensing 59 (1): 597–612. https://doi.org/10.1109/TGRS.2020.2994205.
   Web of Science ®Google Scholar
• Wang, L., and X. Wang. 2022. “Dual-Coupled CNN-GCN-Based Classification for Hyperspectral and LiDAR Data.” Sensors 22 (15): 5735. https://doi.org/10.3390/s22155735.
   PubMed Web of Science ®Google Scholar
• Wang, Y., Y. Sun, Z. Liu, S. E. Sarma, M. M. Bronstein, and J. M. Solomon. 2019. “Dynamic Graph Cnn for Learning on Point Clouds.” ACM Transactions on Graphics (TOG) 38 (5): 1–12. https://doi.org/10.1145/3326362.
   Web of Science ®Google Scholar
• Wu, F., A. Souza, T. Zhang, C. Fifty, T. Yu, and K. Weinberger. 2019. “Simplifying Graph Convolutional Networks.” In International conference on machine learning, Long Beach, CA, USA, 6861–6871. PMLR.
   Google Scholar
• Xu, K., C. Li, Y. Tian, T. Sonobe, K.-I. Kawarabayashi, and S. Jegelka. 2018. “Representation Learning on Graphs with Jumping Knowledge Networks.” In International conference on machine learning, Stockholm, Sweden, 5453–5462. PMLR.
   Google Scholar
• Yan, L., M. Zhao, X. Wang, Y. Zhang, and J. Chen. 2021. “Object Detection in Hyperspectral Images.” IEEE Signal Processing Letters 28:508–512. https://doi.org/10.1109/LSP.2021.3059204.
   Web of Science ®Google Scholar
• Ying, R., R. He, K. Chen, P. Eksombatchai, W. L. Hamilton, and J. Leskovec. 2018. “Graph Convolutional Neural Networks for Web-Scale Recommender Systems.” In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, London, United Kingdom, 974–983.
   Google Scholar
• Yu, Q., W. Wei, Z. Pan, J. He, S. Wang, and D. Hong. 2023. “GPF-Net: Graph-Polarized Fusion Network for Hyperspectral Image Classification.” IEEE Transactions on Geoscience & Remote Sensing 61:1–22. https://doi.org/10.1109/TGRS.2023.3304311.
   Google Scholar
• Yu, W., S. Wan, G. Li, J. Yang, and C. Gong. 2023. “Hyperspectral Image Classification with Contrastive Graph Convolutional Network.” IEEE Transactions on Geoscience & Remote Sensing 61:1–15. https://doi.org/10.1109/TGRS.2023.3240721.
   Google Scholar
• Zhang, M., Z. Cui, M. Neumann, and Y. Chen. 2018. “An End-To-End Deep Learning Architecture for Graph Classification.” In Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA, 32.
   Google Scholar
• Zhao, L., and L. Akoglu. 2020. “Pairnorm: Tackling Oversmoothing in Gnns.” The Eighth International Conference on Learning Representations (ICLR 2020), Virtual Conference. https://openreview.net/pdf?id=rkecl1rtwB.
   Google Scholar
• Zhuang, H., C. Wang, C. Li, Q. Wang, and X. Zhou. 2017. “Natural Language Processing Service Based on Stroke-Level Convolutional Networks for Chinese Text Classification.” In 2017 IEEE international conference on web services (ICWS), Honolulu, Hawaii, USA, 404–411. IEEE.
   Google Scholar