End-to-End Learning to Index and Search in Large Output Spaces
Nov 28, 2022
Speakers
Nilesh Gupta
Speaker · 0 followers
Patrick H. Chen
Speaker · 0 followers
Hsiang-Fu Yu
Speaker · 0 followers
Cho-Jui Hsieh
Speaker · 0 followers
Inderjit S. Dhillon
Speaker · 0 followers
About
Extreme multi-label classification (XMC) is a popular framework for solving many real-world problems that require accurate prediction from a very large number of potential output choices. A popular approach for dealing with the large label space is to arrange the labels into a shallow tree-based index and then learn an ML model to efficiently search this index via beam search. Existing methods initialize the tree index by clustering the label space into a few mutually exclusive clusters based on pre-defined features and keep it fixed throughout the training procedure. This approach results in a sub-optimal indexing structure over the label space and limits the search performance to the quality of choices made during the initialization of the index. In this paper, we propose a novel method ELIAS which relaxes the tree-based index to a specialized weighted graph based index which is learned end-to-end with the final task objective. More specifically, ELIAS models the discrete label-to-cluster assignments in the existing tree-based index as soft learnable parameters that are learned jointly with the rest of the ML model. ELIAS achieves state-of-the-art performance on several large-scale extreme classification benchmarks with millions of labels. In particular, ELIAS can be up to 2.5Extreme multi-label classification (XMC) is a popular framework for solving many real-world problems that require accurate prediction from a very large number of potential output choices. A popular approach for dealing with the large label space is to arrange the labels into a shallow tree-based index and then learn an ML model to efficiently search this index via beam search. Existing methods initialize the tree index by clustering the label space into a few mutually exclusive clusters based on…
Organizer
NeurIPS 2022
Account · 957 followers
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
Structured Energy Network As a Loss function
Watch later
Jay Yoon Lee, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Reinforcement Learning in System Identification
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Closing Remarks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Invited Panel 1: AI Curating Culture
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Unified Sequence Interface for Vision Tasks
Watch later
Ting Chen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning
Watch later
Xiang Chen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%