Timezone: »

 
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
Jaehyun Nam · Jihoon Tack · Kyungmin Lee · Hankook Lee · Jinwoo Shin

@
in Table Representation Learning »
Event URL: https://openreview.net/forum?id=UdgnVBO7MoM »

Learning with few-labeled tabular samples is an essential requirement for industrial machine learning applications as varieties of tabular data suffer from high annotation costs or have difficulties in collecting new samples for novel tasks. Despite the utter importance, such a problem is quite under-explored in the field of tabular learning, and existing few-shot learning schemes from other domains are not straightforward to apply, mainly due to the heterogeneous characteristics of tabular data. In this paper, we propose a simple yet effective framework for few-shot tabular learning, coined Self-generated Tasks from UNlabeled Tables (STUNT). Our key idea is to self-generate diverse few-shot tasks by treating randomly chosen columns as a target label. We then employ a meta-learning scheme to learn generalizable knowledge over the constructed tasks. Moreover, we introduce an unsupervised validation scheme for hyperparameter search (and early stopping) by generating a pseudo-validation set using STUNT from unlabeled data. Our experimental results demonstrate that our simple framework brings significant performance gain under various tabular few-shot learning benchmarks, compared to prior semi- and self-supervised baselines.

Keywords: Few-Shot Learning · Tabular representation learning · Unsupervised meta-learning

Author Information

Jaehyun Nam (Korea Advanced Institute of Science & Technology)
Jihoon Tack (KAIST)
Kyungmin Lee (Korea Advanced Institute of Science & Technology)
Hankook Lee (Korea Advanced Institute of Science and Technology)
Jinwoo Shin (KAIST)

More from the Same Authors