Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning

Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth. While a variety of label disambiguation methods have been proposed in this domain, they normally assume a class-balanced scenario that may not hold in many real-world applications. Empirically, we observe degenerated performance of the prior methods when facing the combinatorial challenge from the long-tailed distribution and partial-labeling. In this work, we first identify the major reasons that the prior…

ImbaGCD：不平衡的广义类别发现

ImbaGCD: Imbalanced Generalized Category Discovery

本文针对无标注数据中已知类别多于未知类别的不平衡广义类别发现问题，提出基于最优传输的期望最大化框架ImbaGCD，通过估计并对齐类别先验分布，在CIFAR-100和ImageNet-100上显著超越现有方法。

Energy Aligning for Biased Models

Training on class-imbalanced data usually results in biased models that tend to predict samples into the majority classes, which is a common and notorious problem. From the perspective of energy-based model, we demonstrate that the free energies of categories are aligned with the label distribution theoretically, thus the energies of different classes are expected to be close to each other when aiming for ``balanced'' performance. However, we discover a severe energy-bias phenomenon in the models trained on class-imbalanced dataset. To eliminate the bias, we propose a simple and effective meth…

SMOGAN：基于GAN优化的不平衡回归合成少数类过采样

SMOGAN: Synthetic Minority Oversampling with GAN Refinement for Imbalanced Regression

针对不平衡回归中数据分布复杂非线性导致现有合成数据不准确的问题，提出两步过采样框架SMOGAN，利用分布感知GAN（DistGAN）作为过滤层优化初始合成样本，使其对齐真实联合分布，在23个数据集上显著优于默认方法。

CCNETS：一种用于不平衡数据集模式识别的模块化因果学习框架

CCNETS: A Modular Causal Learning Framework for Pattern Recognition in Imbalanced Datasets

针对不平衡数据中生成与分类独立导致的分布不匹配问题，提出因果协同框架CCNETS，集成生成、推理与重建，通过因果反馈和Zoint机制实现特征自适应融合，在欺诈检测等极端不平衡任务中显著提升分类性能与泛化能力。

对齐人类与机器注意力以增强监督学习

Aligning Human and Machine Attention for Enhanced Supervised Learning

本文提出 HuMAL 方法，利用人类自我感知注意力标注数据增强监督学习，并在情感分析和人格分类任务中显著提升 BERT、GPT-2 与 XLNET 在稀疏或不平衡标签条件下的性能。