Timezone: »

On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training
Jieyu Zhang · Bohan Wang · Zhengyu Hu · Pang Wei Koh · Alexander Ratner

Wed Dec 13 08:45 AM -- 10:45 AM (PST) @ Great Hall & Hall B1+B2 #429

Pre-training datasets are critical for building state-of-the-art machine learning models, motivating rigorous study on their impact on downstream tasks. In this work, we study the impact of the trade-off between the intra-class diversity (the number of samples per class) and the inter-class diversity (the number of classes) of a supervised pre-training dataset. Empirically, we found that with the size of the pre-training dataset fixed, the best downstream performance comes with a balance on the intra-/inter-class diversity. To understand the underlying mechanism, we show theoretically that the downstream performance depends monotonically on both types of diversity. Notably, our theory reveals that the optimal class-to-sample ratio (#classes / #samples per class) is invariant to the size of the pre-training dataset, which motivates an application of predicting the optimal number of pre-training classes. We demonstrate the effectiveness of this application by an improvement of around 2 points on the downstream tasks when using ImageNet as the pre-training dataset.

Author Information

Jieyu Zhang (Department of Computer Science, University of Washington)
Bohan Wang (USTC)
Zhengyu Hu (HKUST)
Pang Wei Koh (University of Washington)
Alexander Ratner (Stanford University)

More from the Same Authors