{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T12:05:13Z","timestamp":1772193913673,"version":"3.50.1"},"reference-count":41,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T00:00:00Z","timestamp":1772064000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Anhui Provincial Scientific Research Project of Higher Education Institutions","award":["2022AH052464"],"award-info":[{"award-number":["2022AH052464"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Deep learning models typically rely on large-scale datasets with accurate annotations, yet real-world applications inevitably suffer from label noise, which severely degrades generalization\u2014particularly for lightweight neural networks with limited capacity. Existing learning with noisy labels methods are mainly designed for over-parameterized models and are often unsuitable for resource-constrained deployment. To address this challenge, we propose a robust framework that integrates a Micro Hybrid Attention Module (MHAM) with knowledge distillation (KD) for lightweight architectures such as MobileNetV3. MHAM employs a decoupled channel\u2013spatial attention design to enhance discriminative feature extraction while suppressing noise-sensitive background responses. From a graph\u2013signal perspective, MHAM can be interpreted as a spectral smoothing operator that improves optimization stability. In addition, knowledge distillation with soft teacher supervision mitigates overfitting to corrupted hard labels and reduces prediction uncertainty. Extensive experiments demonstrate the effectiveness of the proposed method. On FER2013, a real-world noisy facial expression recognition benchmark, our approach achieves 68.5% accuracy with only 0.52M parameters, while reducing optimization variance by 24%. On CIFAR-10 with 40% symmetric label noise, it improves accuracy from 54.85% to 60.10%. On CIFAR-10N with multiple types of real-world human annotation noise, the proposed method consistently achieves 63.9\u201371.9% accuracy under different noise protocols. These results show that the proposed framework provides an efficient and robust solution for noisy label learning in lightweight facial expression and object classification on edge devices.<\/jats:p>","DOI":"10.3390\/a19030177","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T13:58:03Z","timestamp":1772114283000},"page":"177","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Lightweight Convolutional Networks via Topological Attention and Entropy-Constrained Distillation: A Spectral\u2013Topological Approach for Robust Facial Expression Recognition"],"prefix":"10.3390","volume":"19","author":[{"given":"Xiaohong","family":"Dong","sequence":"first","affiliation":[{"name":"Department of Architecture and Art, City University of Hefei, No. 1 Shuxiang Road, Huanglu Science and Education Park, Hefei 238076, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Architecture and Art, City University of Hefei, No. 1 Shuxiang Road, Huanglu Science and Education Park, Hefei 238076, China"},{"name":"The School of Civil Engineering, Anhui Jianzhu University, No. 292 Ziyun Road, Hefei Economic and Technological Development Zone, Hefei 230601, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Anhui Engineering and Construction Magazine, No. 996 Ziyun Road, Baohe District, Hefei 230091, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxiaoman","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Architecture, Planning and Landscape Architecture, University of Arizona, 1040 N Olive Rd., Tucson, AZ 85719, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/3446776","article-title":"Understanding deep learning (still) requires rethinking generalization","volume":"64","author":"Zhang","year":"2021","journal-title":"Commun. ACM"},{"key":"ref_2","unstructured":"Arpit, D., Jastrz\u0119bski, S., Ballas, N., Krueger, D., Bengio, E., Kanwal, M.S., Maharaj, T., Fischer, A., Courville, A., and Bengio, Y. (2017). A closer look at memorization in deep networks. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3578580","article-title":"A universal law of robustness via isoperimetry","volume":"70","author":"Bubeck","year":"2022","journal-title":"J. ACM"},{"key":"ref_4","first-page":"378","article-title":"The coherence and robustness analysis for a family of unbalanced networks","volume":"11","author":"Liu","year":"2025","journal-title":"IEEE Trans. Signal Inf. Process. Netw."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4719","DOI":"10.1109\/TNSE.2024.3395710","article-title":"The coherence and properties analysis of balanced 2^p-ary tree networks","volume":"11","author":"Liu","year":"2024","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"ref_6","unstructured":"Foret, P., Kleiner, A., Mobahi, H., and Neyshabur, B. (2020). Sharpness-aware minimization for efficiently improving generalization. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","article-title":"Squeeze-and-excitation networks","volume":"42","author":"Hu","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018, January 8\u201314). CBAM: Convolutional block attention module. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_10","unstructured":"Chaudhari, P., and Soatto, S. (2015). On the energy landscape of deep networks. arXiv."},{"key":"ref_11","unstructured":"Zhang, Y., Liang, P., and Wainwright, M.J. (2017, January 6\u201311). Convexified convolutional neural networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1109\/TIT.2022.3215088","article-title":"On generalization bounds for deep networks based on loss surface implicit regularization","volume":"69","author":"Imaizumi","year":"2023","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., and Feng, J. (2021, January 19\u201325). Coordinate attention for efficient mobile network design. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 14\u201319). ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref_15","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the knowledge in a neural network. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yuan, L., Tay, F.E.H., Li, G., Wang, T., and Feng, J. (2020, January 13\u201319). Revisiting knowledge distillation via label smoothing regularization. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"ref_17","unstructured":"M\u00fcller, R., Kornblith, S., and Hinton, G. (2019, January 8\u201314). When does label smoothing help?. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_19","unstructured":"Phuong, M., and Lampert, C. (2019, January 9\u201315). Towards understanding knowledge distillation. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_20","unstructured":"Menon, A.K., Rawat, A.S., Reddi, S.J., Kim, S., and Kumar, S. (2021, January 18\u201324). A statistical perspective on distillation. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_21","unstructured":"La Malfa, E., La Malfa, G., Caprioli, C., Nicosia, G., and Latora, V. (2022). Deep neural networks as complex networks. arXiv."},{"key":"ref_22","unstructured":"Liao, Q., Miranda, T., Banburski, A., Hidary, J., and Poggio, T. (2018). A surprising linear relationship predicts test performance in deep networks. arXiv."},{"key":"ref_23","unstructured":"La Malfa, E., La Malfa, G., Nicosia, G., and Latora, V. (2024). Deep neural networks via complex network theory: A perspective. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.neunet.2014.09.005","article-title":"Challenges in representation learning: A report on three machine learning contests","volume":"64","author":"Goodfellow","year":"2015","journal-title":"Neural Netw."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chen, S., Wang, J., Chen, Y., Shi, Z., Geng, X., and Rui, Y. (2020, January 13\u201319). Label distribution learning on auxiliary label space graphs for facial expression recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01400"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, K., Peng, X., Yang, J., Lu, S., and Qiao, Y. (2020, January 13\u201319). Suppressing uncertainties for large-scale facial expression recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, C., Ling, X., and Deng, W. (2022, January 23\u201327). Learn from all: Erasing attention consistency for noisy label facial expression recognition. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/MSP.2012.2235192","article-title":"The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains","volume":"30","author":"Shuman","year":"2013","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1109\/JPROC.2018.2820126","article-title":"Graph signal processing: Overview, challenges, and applications","volume":"106","author":"Ortega","year":"2018","journal-title":"Proc. IEEE"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/BF01164627","article-title":"Resistance distance","volume":"12","author":"Klein","year":"1993","journal-title":"J. Math. Chem."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1109\/TAFFC.2018.2817622","article-title":"EEG emotion recognition using dynamical graph convolutional neural networks","volume":"11","author":"Song","year":"2020","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.physrep.2016.05.004","article-title":"Vital nodes identification in complex networks","volume":"650","author":"Chen","year":"2016","journal-title":"Phys. Rep."},{"key":"ref_33","unstructured":"Dong, Y., Cordonnier, J.-B., and Loukas, A. (2021, January 18\u201324). Attention is not all you need: Pure attention loses rank doubly exponentially with depth. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tishby, N., and Zaslavsky, N. (May, January 26). Deep learning and the information bottleneck principle. Proceedings of the 2015 IEEE Information Theory Workshop (ITW), Jerusalem, Israel.","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1109\/TKDE.2020.2981333","article-title":"Deep learning on graphs: A survey","volume":"34","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_36","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very deep convolutional networks for large-scale image recognition. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_37","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18\u201323). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., and Sun, J. (2018, January 8\u201314). ShuffleNet V2: Practical guidelines for efficient CNN architecture design. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"79327","DOI":"10.1109\/ACCESS.2024.3407108","article-title":"PAtt-lite: Lightweight patch and attention MobileNet for challenging facial expression recognition","volume":"12","author":"Ngwe","year":"2024","journal-title":"IEEE Access"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1290","DOI":"10.1109\/TAFFC.2020.2994159","article-title":"EEG-based emotion recognition using regularized graph neural networks","volume":"13","author":"Zhong","year":"2022","journal-title":"IEEE Trans. Affect. Comput."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/3\/177\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T10:48:22Z","timestamp":1772189302000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/3\/177"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,26]]},"references-count":41,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["a19030177"],"URL":"https:\/\/doi.org\/10.3390\/a19030177","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,26]]}}}