通过张量分解检查持续学习模型内部表示的变化
Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decomposition
AI总结：
本文提出一种基于张量分解的持续学习模型评估框架，通过分析内部表示变化来揭示策略优劣，发现其能反映性能差异但难以直接识别神经元簇。
摘要：
持续学习（CL）推动了多种方法的开发，这些方法旨在跨顺序学习整合先前知识。然而，对这些方法的评估主要集中于最终输出，例如预测类别准确率的变化，而忽视了模型内部的表示遗忘问题。在本文中，我们提出了一种新颖的基于表示的CL模型评估框架。该方法涉及从整个持续学习过程中收集内部表示，并构建三维张量。这些张量是通过堆叠来自多个输入和模型“快照”的表示（如层激活）在学习过程中生成的。通过进行张量分量分析（TCA），我们旨在揭示关于内部表示如何演变的有意义模式，期望突出所研究的CL策略的优点或缺点。我们针对不同的模型架构和基于重要性的持续学习策略进行了分析，并精心选择了任务。虽然我们的方法结果反映了各种CL策略性能的差异，但我们发现我们的方法并未直接突出专门的神经元簇，也未提供对过滤器演变的直接理解。我们相信，我们方法的缩小版本将为使用TCA研究持续学习动态的益处和陷阱提供见解。
英文摘要：
Continual learning (CL) has spurred the development of several methods aimed at consolidating previous knowledge across sequential learning. Yet, the evaluations of these methods have primarily focused on the final output, such as changes in the accuracy of predicted classes, overlooking the issue of representational forgetting within the model. In this paper, we propose a novel representation-based evaluation framework for CL models. This approach involves gathering internal representations from throughout the continual learning process and formulating three-dimensional tensors. The tensors are formed by stacking representations, such as layer activations, generated from several inputs and model `snapshots', throughout the learning process. By conducting tensor component analysis (TCA), we aim to uncover meaningful patterns about how the internal representations evolve, expecting to highlight the merits or shortcomings of examined CL strategies. We conduct our analyses across different model architectures and importance-based continual learning strategies, with a curated task selection. While the results of our approach mirror the difference in performance of various CL strategies, we found that our methodology did not directly highlight specialized clusters of neurons, nor provide an immediate understanding the evolution of filters. We believe a scaled down version of our approach will provide insight into the benefits and pitfalls of using TCA to study continual learning dynamics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
