SemSup-XC: Semantic Supervision for Zero-Shot and Few-Shot Extreme Classification
Jul 24, 2023
Speakers
Pranjal Aggarwal
Speaker · 0 followers
Ameet Deshpande
Speaker · 0 followers
Karthik Narasimhan
Speaker · 2 followers
About
Extreme classification (XC) involves predicting over large numbers of classes (thousands to millions), with real-world applications like news article classification and e-commerce product tagging. The zero-shot version of this task requires generalization to novel classes without additional supervision. In this paper, we develop SemSup-XC, a model that achieves state-of-the-art zero-shot and few-shot performance on three XC datasets derived from legal, e-commerce, and Wikipedia data. To develop SemSup-XC, we use automatically collected semantic class descriptions to represent classes and facilitate generalization through a novel hybrid matching module that matches input instances to class descriptions using a combination of semantic and lexical similarity. Trained with contrastive learning, SemSup-XC significantly outperforms baselines and establishes state-of-the-art performance on all three datasets considered, gaining up to 12 precision points on zero-shot and more than 10 precision points on one-shot tests, with similar gains for recall@10. Our ablation studies highlight the relative importance of our hybrid matching module and automatically collected class descriptions.Extreme classification (XC) involves predicting over large numbers of classes (thousands to millions), with real-world applications like news article classification and e-commerce product tagging. The zero-shot version of this task requires generalization to novel classes without additional supervision. In this paper, we develop SemSup-XC, a model that achieves state-of-the-art zero-shot and few-shot performance on three XC datasets derived from legal, e-commerce, and Wikipedia data. To develop…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Why does Throwing Away Data Improve Worst-Group Error?
Watch later
Image Restoration with Mean-Reverting Stochastic Differential Equations
Watch later
Ziwei Luo, …
AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
Watch later
Generalization on the Unseen, Logic Reasoning and Degree Curriculum
Watch later
TabLeak: Tabular Data Leakage in Federated Learning
Watch later
Mark Vero, …