论文标题
元学习多样性的影响
The Effect of Diversity in Meta-Learning
论文作者
论文摘要
最近的研究表明，任务分配在元学习者的表现中起着至关重要的作用。传统的观点是，任务多样性应该改善元学习的绩效。在这项工作中，我们找到了相反的证据。 （i）我们的实验质疑我们学到的模型的功效：可以通过数据子集（较低的任务多样性）学习相似的流形。这一发现质疑为模型提供更多数据的优势，（ii）为任务分布增加多样性（较高的任务多样性）有时会阻碍模型，并且不会像以前认为的那样导致性能的显着改善。为了加强我们的发现，我们提供了经验和理论证据。
Recent studies show that task distribution plays a vital role in the meta-learner's performance. Conventional wisdom is that task diversity should improve the performance of meta-learning. In this work, we find evidence to the contrary; (i) our experiments draw into question the efficacy of our learned models: similar manifolds can be learned with a subset of the data (lower task diversity). This finding questions the advantage of providing more data to the model, and (ii) adding diversity to the task distribution (higher task diversity) sometimes hinders the model and does not lead to a significant improvement in performance as previously believed. To strengthen our findings, we provide both empirical and theoretical evidence.
