通过多头一致性增强，提升半监督文本分类的准确率与鲁棒性。
MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification
- 基于多头一致性和置信度筛选伪标签并动态加权。
- 在10个数据集上8次达到顶尖水平，平均性能领先第二名3.26%。
- 特别适合标签分布不均的真实场景文本分类任务。
我们提出MultiMatch，一种结合协同训练与一致性正则化思想的半监督学习算法。其核心是伪标签加权模块，根据多头预测一致性和模型置信度筛选并加权伪标签，同时考虑分类难度。该模块整合了多头一致性（来自Multihead Co-training）、自适应阈值（来自FreeMatch）和平均伪边界（来自MarginMatch）三种技术，形成统一框架，显著提升半监督场景下的鲁棒性与性能。在5个自然语言处理基准数据集上的实验表明，MultiMatch在10个测试设置中取得8个最优结果，且在21种方法的弗里德曼检验中排名第一。此外，在高度不平衡数据下表现尤为突出，相比第二优方法提升3.26%，对真实文本分类任务具有重要意义。代码已开源。
原文摘要 · Abstract (English)
We introduce MultiMatch, a novel semi-supervised learning (SSL) algorithm combining the paradigms of co-training and consistency regularization with pseudo-labeling. At its core, MultiMatch features a pseudo-label weighting module designed for selecting and filtering pseudo-labels based on head agreement and model confidence, and weighting them according to the perceived classification difficulty. This novel module enhances and unifies three existing techniques -- heads agreement from Multihead Co-training, self-adaptive thresholds from FreeMatch, and Average Pseudo-Margins from MarginMatch -- resulting in a holistic approach that improves robustness and performance in SSL settings. Experimental results on benchmark datasets highlight the superior performance of MultiMatch, i.e., MultiMatch achieves state-of-the-art results on 8 out of 10 setups from 5 natural language processing datasets and ranks first according to the Friedman test among 21 methods. Furthermore, MultiMatch demonstrates exceptional robustness in highly imbalanced settings, outperforming the second-best approach by 3.26%, a critical advantage for real-world text classification tasks. Our code is available on GitHub.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。