{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T17:59:31Z","timestamp":1761760771260,"version":"build-2065373602"},"reference-count":36,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>This paper investigates the role of symmetry and asymmetry in the learning process of modern machine learning models, with a specific focus on feature representation and optimization. We introduce a novel symmetry-aware learning framework that identifies and preserves symmetric properties within high-dimensional datasets, while allowing model asymmetries to capture essential discriminative cues. Through analytical modeling and empirical evaluations on benchmark datasets, we demonstrate how symmetrical transformations of features (e.g., rotation, mirroring, permutation invariance) impact learning efficiency, interpretability, and generalization. Furthermore, we explore asymmetric regularization techniques that prioritize informative deviations from symmetry in model parameters, thereby improving classification and clustering performance. The proposed approach is validated using a variety of classifiers including neural networks and tested across domains such as image recognition, biomedical data, and social networks. Our findings highlight the critical importance of leveraging domain-specific symmetries to enhance both the performance and explainability of machine learning systems.<\/jats:p>","DOI":"10.3390\/sym17111821","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T17:38:22Z","timestamp":1761759502000},"page":"1821","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Symmetry-Aware Feature Representations and Model Optimization for Interpretable Machine Learning"],"prefix":"10.3390","volume":"17","author":[{"given":"Mehtab","family":"Alam","sequence":"first","affiliation":[{"name":"Department of Computer Science, Acharya Narendra Dev College, University of Delhi, Delhi 110019, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6794-3677","authenticated-orcid":false,"given":"Abdullah","family":"Alourani","sequence":"additional","affiliation":[{"name":"Department of Management Information Systems, College of Business and Economics, Qassim University, Buraydah 51452, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4769-5407","authenticated-orcid":false,"given":"Ashraf","family":"Ali","sequence":"additional","affiliation":[{"name":"Faculty of Computer Studies, Arab Open University-Bahrain, A\u2019ali P.O. Box 18211, Bahrain"}]},{"given":"Firoj","family":"Ahamad","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Galgotia University, Greater Noida 203201, Uttar Pradesh, India"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/MSP.2017.2693418","article-title":"Geometric Deep Learning: Going beyond Euclidean data","volume":"34","author":"Bronstein","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_2","unstructured":"Cohen, T.S., and Welling, M. (2016, January 19\u201324). Group Equivariant Convolutional Networks. Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA."},{"key":"ref_3","unstructured":"Kondor, R., and Trivedi, S. (2018, January 10\u201315). On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_4","unstructured":"Zaheer, M., Kottur, S., Ravanbakhsh, S., Poczos, B., Salakhutdinov, R.R., and Smola, A.J. (2017). Deep Sets. Advances in Neural Information Processing Systems 30, Neural Information Processing Systems Foundation, Inc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_6","unstructured":"Kipf, T.N., and Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. arXiv."},{"key":"ref_7","unstructured":"Chen, X., Kingma, D.P., Salimans, T., Duan, Y., Dhariwal, P., Schulman, J., Sutskever, I., and Abbeel, P. (2017). Variational Lossy Autoencoder. arXiv."},{"key":"ref_8","unstructured":"Robberechts, P., Van Haaren, J., and Davis, J. A Bayesian Approach to In-Game Win Probability in Soccer. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, New York, NY, USA."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Alam, M., and Khan, I.R. (2022). Application of AI in Smart Cities. Industrial Transformation, CRC Press.","DOI":"10.1201\/9781003229018-4"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"4793","DOI":"10.1109\/TNNLS.2020.3027314","article-title":"A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI","volume":"32","author":"Tjoa","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_11","unstructured":"Satorras, V.G., Hoogeboom, E., and Welling, M. (2022, January 18\u201324). E(n) Equivariant Graph Neural Networks. Proceedings of the 38th International Conference on Machine Learning, Virtual."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.4007\/annals.2022.195.3.5","article-title":"A negative answer to Ulam\u2019s Problem 19 from the Scottish Book","volume":"195","author":"Ryabogin","year":"2022","journal-title":"Ann. Math."},{"key":"ref_13","unstructured":"Santos-Escriche, E., and Jegelka, S. (2025). Learning Equivariant Models by Discovering Symmetries with Learnable Augmentations. arXiv."},{"key":"ref_14","unstructured":"Ziyin, L., Xu, Y., Poggio, T., and Chuang, I. (2025). Parameter Symmetry Potentially Unifies Deep Learning Theory. arXiv."},{"key":"ref_15","first-page":"62922","article-title":"Clifford Group Equivariant Neural Networks","volume":"36","author":"Ruhe","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_16","unstructured":"Keller, T.A. (2025). Flow Equivariant Recurrent Neural Networks. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"020328","DOI":"10.1103\/PRXQuantum.5.020328","article-title":"Theory for Equivariant Quantum Neural Networks","volume":"5","author":"Nguyen","year":"2024","journal-title":"PRX Quantum"},{"key":"ref_18","unstructured":"Pearce-Crump, E., and Knottenbelt, W.J. (2024). Graph Automorphism Group Equivariant Neural Networks. arXiv."},{"key":"ref_19","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems 30, Neural Information Processing Systems Foundation, Inc."},{"key":"ref_20","unstructured":"Kaba, S.-O., and Ravanbakhsh, S. (2024). Symmetry Breaking and Equivariant Neural Networks. arXiv."},{"key":"ref_21","unstructured":"Hofgard, E., Wang, R., Walters, R., and Smidt, T. (2024). Relaxed Equivariant Graph Neural Networks. arXiv."},{"key":"ref_22","unstructured":"Dhurandhar, A., Chen, P.Y., Luss, R., Tu, C.C., Ting, P., Shanmugam, K., and Das, P. (2018). Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives. Advances in Neural Information Processing Systems 31, Neural Information Processing Systems Foundation, Inc."},{"key":"ref_23","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. (2018, January 10\u201315). Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_24","first-page":"71393","article-title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","volume":"36","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_25","unstructured":"Cohen, A., Koren, T., and Mansour, Y. (2019, January 9\u201315). Learning Linear-Quadratic Regulators Efficiently with only \u221a T Regret. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_26","unstructured":"Bronstein, M.M., Bruna, J., Cohen, T., and Veli\u010dkovi\u0107, P. (2021). Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges. arXiv."},{"key":"ref_27","unstructured":"Finzi, M., Stanton, S., Izmailov, P., and Wilson, A.G. (2025, April 28). Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data. Available online: https:\/\/github.com\/mfinzi\/LieConv."},{"key":"ref_28","unstructured":"Esteves, C. (2020). Theoretical Aspects of Group Equivariant Neural Networks. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.compbiomed.2018.03.016","article-title":"A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification","volume":"96","author":"Yildirim","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"ref_30","unstructured":"Velarde, O., Parra, L., Boldi, P., and Makse, H. (2024). The Role of Fibration Symmetries in Geometric Deep Learning. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1109\/TIT.1962.1057692","article-title":"Visual pattern recognition by moment invariants","volume":"8","author":"Hu","year":"1962","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Larochelle, H., Erhan, D., Courville, A., Bergstra, J., and Bengio, Y. (2007, January 20\u201324). An empirical evaluation of deep architectures on problems with many factors of variation. Proceedings of the 24th International Conference on Machine Learning, Corvalis, OR, USA.","DOI":"10.1145\/1273496.1273556"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"E215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_34","unstructured":"Chen, C., Li, O., Tao, D., Barnett, A., Rudin, C., and Su, J.K. (2019, January 8\u201314). This looks like that: Deep learning for interpretable image recognition. Proceedings of the 33rd International Conference on Neural Information Processing Systems, Red Hook, NY, USA."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u2018Why Should I Trust You?\u2019: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.ins.2017.06.027","article-title":"Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals","volume":"415\u2013416","author":"Acharya","year":"2017","journal-title":"Inf. Sci."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/11\/1821\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T17:55:25Z","timestamp":1761760525000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/11\/1821"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":36,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["sym17111821"],"URL":"https:\/\/doi.org\/10.3390\/sym17111821","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]}}}