通过删减数据让模型适应新领域，提升生物声学检测效果。
Unsupervised Domain Adaptation Via Data Pruning
- 用MMD衡量数据分布差异，智能筛选需删除的训练样本。
- 在真实生物声学任务中，性能超越现有无监督域适应方法。
- 方法可与CORAL等算法配合，适合处理数据分布偏移问题。
从训练数据中精心剔除样本，是提升机器学习模型鲁棒性的有效手段，但最佳剔除策略仍不明确。本文从无监督域适应（UDA）角度出发，提出AdaPrune方法，通过删除训练样本使训练分布更接近目标数据分布。采用最大均值差异（MMD）作为对齐标准，将问题建模为整数二次规划求解。在真实的生物声学事件检测任务中评估表明，该方法优于现有相关技术，并可与CORAL等其他UDA算法互补。对MMD与模型准确率关系的分析及t-SNE可视化结果，验证了该方法在数据剪枝上的合理性与有效性。
原文摘要 · Abstract (English)
The removal of carefully-selected examples from training data has recently emerged as an effective way of improving the robustness of machine learning models. However, the best way to select these examples remains an open question. In this paper, we consider the problem from the perspective of unsupervised domain adaptation (UDA). We propose AdaPrune, a method for UDA whereby training examples are removed to attempt to align the training distribution to that of the target data. By adopting the maximum mean discrepancy (MMD) as the criterion for alignment, the problem can be neatly formulated and solved as an integer quadratic program. We evaluate our approach on a real-world domain shift task of bioacoustic event detection. As a method for UDA, we show that AdaPrune outperforms related techniques, and is complementary to other UDA algorithms such as CORAL. Our analysis of the relationship between the MMD and model accuracy, along with t-SNE plots, validate the proposed method as a principled and well-founded way of performing data pruning.
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。