长尾学习

长尾学习（Long-tail Learning）是人工智能领域的一个重要研究方向，主要关注于处理数据分布中呈现出长尾（long tail）现象的问题。在数据分布中，长尾现象指的是一种非常常见的情况，即少数类别的样本数量远远少于大多数类别的样本数量。这种分布现象在许多现实世界的问题中都存在，如商品销售、自然语言处理中的词频分布、图像识别中的类别分布等。

长尾学习的目标是克服数据分布中长尾部分的挑战，以实现更好的模型性能和预测准确度。这种情况下，传统的机器学习算法可能会面临问题，因为它们更容易在样本数量较多的类别上表现出色，而在样本数量较少的类别上表现较差。

相关成果：

[1] Yang Lu, Yiliang Zhang, Bo Han, Yiu-ming Cheung, Hanzi Wang, “Label-Noise Learning with Intrinsically Long-Tailed Data,” in Proceedings of IEEE/CVF International Conference of Computer Vision (ICCV), Paris, France, October 2-6, 2023. (CCF A)

[2] Yan Jin, Mengke Li, Yang Lu*, Yiu-ming Cheung, and Hanzi Wang, “Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation,” in Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23695-23704, Vancouver, Canada, June 18-22, 2023. (CCF A)

[3] Mengke Li, Yiu-ming Cheung, and Yang Lu, “Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment” in Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.6929-6938 , New Orleans, Louisiana, June 21-24, 2022. (CCF A)

[4] Yang Lu, Yiu-ming Cheung, and Yuan Yan Tang, “Self-Adaptive Multi-Prototype-based Competitive Learning Approach: A k-means-type Algorithm for Imbalanced Data Clustering,” IEEE Transactions on Cybernetics (TCYB), vol. 51, no. 3, pp. 1598-1612, 2021. (JCR 1区/ CCF B)

[5] Yang Lu, Yiu-ming Cheung, and Yuan Yan Tang, “Bayes Imbalance Impact Index: A Measure of Class Imbalanced Dataset for Classification Problem,” IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 31, no. 9, pp. 3525-3539, 2020. (JCR 1区/ CCF B)

[6] Yang Lu, Yiu-ming Cheung, and Yuan Yan Tang, “Adaptive Chunk-based Dynamic Weighted Majority for Imbalanced Data Streams with Concept Drift,” IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 31, no. 8, pp. 2764-2778, 2020. (JCR 1区/ CCF B)