通过构建分层专家森林，让模型在增量学习中更好共享知识。
From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning
- 将任务按语义关系分组，构建层次化专家树以组织适配器。
- 在多个基准数据集上达到当前最优性能，有效缓解遗忘问题。
- 适合需要持续学习新类别且资源受限的场景。
类增量学习（CIL）要求模型在不遗忘旧类的前提下学习新类。常见方法是冻结预训练模型并为每个任务训练轻量级适配器。尽管能防止遗忘，但该方法将已有知识视为无结构集合，忽略了任务间的关联。为此，我们提出语义引导的自适应专家森林（SAEF），通过结构化层级组织适配器以促进知识共享。SAEF首先基于语义关系将任务聚类；随后在每类内通过合并相似任务的适配器构建平衡的专家树。推理时，SAEF根据输入激活一组相关专家，其输出按专家置信度加权融合得到最终预测。在多个基准数据集上的实验表明，SAEF实现了当前最优性能。
原文摘要 · Abstract (English)
Class-Incremental Learning (CIL) requires models to learn new classes without forgetting old ones. A common method is to freeze a pre-trained model and train a new, lightweight adapter for each task. While this prevents forgetting, it treats the learned knowledge as a simple, unstructured collection and fails to use the relationships between tasks. To this end, we propose the Semantic-guided Adaptive Expert Forest (SAEF), a new method that organizes adapters into a structured hierarchy for better knowledge sharing. SAEF first groups tasks into conceptual clusters based on their semantic relationships. Then, within each cluster, it builds a balanced expert tree by creating new adapters from merging the adapters of similar tasks. At inference time, SAEF finds and activates a set of relevant experts from the forest for any given input. The final prediction is made by combining the outputs of these activated experts, weighted by how confident each expert is. Experiments on several benchmark datasets show that SAEF achieves SOTA performance.
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。