[论文解读] Representative Task Self-selection for Flexible Clustered Lifelong Learning
该论文提出FCL³,一种灵活的聚类持续学习框架,通过稀疏自编码器动态维护特征学习库,并通过代表性任务自选择机制增量更新模型知识库。通过在新任务为异常值时自适应地添加新的代表性模型,而在其他情况下优化共享表征,FCL³在真实世界数据集上的表现优于现有的持续学习与批量聚类多任务学习方法。
Consider the lifelong machine learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e.g., knowledge library or deep network weights. However, the knowledge libraries or deep networks for most recent lifelong learning models are with prescribed size, and can degenerate the performance for both learned tasks and coming ones when facing with a new task environment (cluster). To address this challenge, we propose a novel incremental clustered lifelong learning framework with two knowledge libraries: feature learning library and model knowledge library, called Flexible Clustered Lifelong Learning (FCL3). Specifically, the feature learning library modeled by an autoencoder architecture maintains a set of representation common across all the observed tasks, and the model knowledge library can be self-selected by identifying and adding new representative models (clusters). When a new task arrives, our proposed FCL3model firstly transfers knowledge from these libraries to encode the new task, i.e.,effectively and selectively soft-assigning this new task to multiple representative models over feature learning library. Then, 1) the new task with a higher outlier probability will be judged as a new representative, and used to redefine both feature learning library and representative models over time; or 2) the new task with lower outlier probability will only refine the feature learning library. For model optimization, we cast this lifelong learning problem as an alternating direction minimization problem as a new task comes. Finally, we evaluate the proposed framework by analyzing several multi-task datasets, and the experimental results demonstrate that our FCL3 model can achieve better performance than most lifelong learning frameworks, even batch clustered multi-task learning models.
研究动机与目标
- 解决持续学习中固定大小知识库的局限性,该局限性在面对新型未知任务环境时会导致性能下降。
- 在动态环境中实现先前学习任务与新任务(可能无关)之间的有效知识迁移。
- 开发一种持续学习系统,可在新任务环境出现时自选并增量添加代表性模型(聚类)。
- 在保持模型知识随时间演化的前提下,维护所有任务之间的共享判别性特征表征。
- 在性能上优于批量聚类多任务学习与当前最先进持续学习框架。
提出的方法
- FCL³采用两个知识库:基于稀疏自编码器的特征学习库,用于在任务间学习共享且具有判别性的表征。
- 通过识别并添加新代表性模型,当新任务被判定为异常值(高异常概率)时,增量更新模型知识库。
- 通过在模型库中对新任务进行软分配至多个代表性模型,实现知识迁移,同时利用稀疏性约束确保选择性与有效性。
- 该框架将持续学习问题建模为交替方向乘子法(ADMM)求解的交替方向最小化问题。
- 通过在表征空间中使用基于距离的度量进行异常值检测,并利用泰勒展开近似围绕代表性模型的新任务学习过程。
- 通过交替优化方案联合优化特征表征与模型分配,既保留历史知识,又能适应新任务。
实验结果
研究问题
- RQ1持续学习系统能否动态扩展其模型库以容纳新型未知任务环境,同时不降低对先前任务的性能?
- RQ2在聚类持续学习设置中,如何在先前学习任务与新任务(可能无关)之间实现有效的知识迁移?
- RQ3与固定或预定义模型库相比,代表性模型的自选机制在多大程度上能提升性能?
- RQ4基于稀疏自编码器的特征学习库能否增强在多样化任务上的泛化与迁移性能?
- RQ5与标准持续学习和批量聚类多任务学习相比,所提出的FCL³框架在准确率与适应性方面表现如何?
主要发现
- FCL³在多个多任务数据集(包括School与Landmine)上优于大多数持续学习框架。
- 在Landmine数据集上,FCL³达到79.022% ± 0.42的AUC,优于基线方法。
- 在School数据集上,FCL³实现9.985 ± 0.03的RMSE,表现出强劲的回归性能。
- 稀疏自编码器架构显著提升了特征表征质量,其中Ours-Rand(无解码器)表现出明显性能下降,证实了其重要性。
- 统一框架(Ours-woDecoder)优于两阶段方法CL3-Rand,表明端到端优化具有优势。
- 基于ADMM的优化方法有效求解了交替最小化问题,实现了跨任务的稳定且收敛的学习。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。