对比整合上行调节实现稀疏监督连续学习
Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
AI总结：
任务调节对比学习通过上行调节实现稀疏监督下的连续学习，提升类别增量和迁移学习性能。
摘要：
生物大脑从连续的无标签数据流中持续学习，同时在不损害其泛化能力的前提下，整合来自稀疏标注示例的专业信息。与此同时，在这种自然学习设置中，机器学习方法容易出现灾难性遗忘，因为监督式专业微调会降低原始任务的性能。我们引入了任务调节对比学习（TMCL），其灵感来自新皮层中的生物物理机制，利用预测编码原理持续整合上行信息并无需监督。我们遵循这些原理构建视图不变表示空间的想法，并认为这可以通过对比损失实现。然后，每当出现新类别的标注样本时，会学习新的仿射调节，以提高新类别与其他类别的分离度，而不影响前馈权重。通过利用视图不变学习机制，我们然后训练前馈权重，使数据样本的未调节表示与调节后的对应物匹配。这将调节不变性引入表示空间，并通过使用过去的调节来稳定它。我们的实验表明，在使用仅1%可用标签的情况下，相对于最先进的无监督方法以及可比的监督方法，在类别增量学习和迁移学习方面均取得了改进。总体而言，我们的工作表明，上行调节在平衡稳定性和可塑性方面发挥着关键作用。
英文摘要：
Biological brains learn continually from a stream of unlabeled data, while integrating specialized information from sparsely labeled examples without compromising their ability to generalize. Meanwhile, machine learning methods are susceptible to catastrophic forgetting in this natural learning setting, as supervised specialist fine-tuning degrades performance on the original task. We introduce task-modulated contrastive learning (TMCL), which takes inspiration from the biophysical machinery in the neocortex, using predictive coding principles to integrate top-down information continually and without supervision. We follow the idea that these principles build a view-invariant representation space, and that this can be implemented using a contrastive loss. Then, whenever labeled samples of a new class occur, new affine modulations are learned that improve separation of the new class from all others, without affecting feedforward weights. By co-opting the view-invariance learning mechanism, we then train feedforward weights to match the unmodulated representation of a data sample to its modulated counterparts. This introduces modulation invariance into the representation space, and, by also using past modulations, stabilizes it. Our experiments show improvements in both class-incremental and transfer learning over state-of-the-art unsupervised approaches, as well as over comparable supervised approaches, using as few as 1% of available labels. Taken together, our work suggests that top-down modulations play a crucial role in balancing stability and plasticity.
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。
