End-to-End Learning to Index and Search in Large Output Spaces
28. listopadu 2022
Řečníci
Nilesh Gupta
Řečník · 0 sledujících
Patrick H. Chen
Řečník · 0 sledujících
Hsiang-Fu Yu
Řečník · 0 sledujících
Cho-Jui Hsieh
Řečník · 0 sledujících
Inderjit S. Dhillon
Řečník · 0 sledujících
O prezentaci
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…
Organizátor
NeurIPS 2022
Účet · 960 sledujících
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks
Zhlédnout později
Zhiyang Chen, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Random Rank: The One and Only Strategyproof and Proportionally Fair Randomized Facility Location Mechanism
Zhlédnout později
Haris Aziz, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Multimodal deep learning system for anxiety and depression detection
Zhlédnout později
Brian Diep, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Quadratic minimization: from conjugate gradients to an adaptive heavy-ball method with Polyak step-sizes
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %