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 · 961 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
AutoMS: Automatic Model Selection for Novelty Detection with Error Rate Control
Watch later
Yifan Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Opening Remarks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Temperature impacts on hate speech online: evidence from four billion tweets
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Opening Remarks: Foundation Models for Decision Making
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
An Unsupervised Learning Perspective on the Dynamic Contribution to Extreme Precipitation Changes
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Attending to what's not there
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%