AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces

Chuan Guo, Ali Mousavi, Xiang Wu, Daniel N Holtmann-Rice, Satyen Kale, Sashank Reddi, Sanjiv Kumar

NeurIPS 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 35 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add GLaS regularizer (ablation)embedding-based model · AmazonCat-13KP@1: 92.34 -> 94.21Improved
GLaS instead of spread-out regularizer (ablation)embedding-based model · AmazonCat-13KP@1: 93.34 -> 94.21Improved
GLaS instead of Gravity regularizer (ablation)embedding-based model · AmazonCat-13KP@1: 93.42 -> 94.21Improved
add GLaS regularizer (ablation)embedding-based model · AmazonCat-13Kgeneralization gap: 6.89 -> 4.56Improved
add GLaS regularizer (ablation)embedding-based model · Amazon-670Ktest accuracy: 44.53 -> 46.32Improved
add input dropout (rho=0.8) (ablation)embedding-based model · AmazonCat-13KP@1: 93.39 -> 94.21Improved
use nonlinear ReLU embedding instead of linear (ablation)embedding-based model · AmazonCat-13KP@1: 91.77 -> 94.21Improved
increase embedding size from 256 to 1024 (ablation)embedding-based model · AmazonCat-13KP@1: 93.24 -> 94.21Improved
increase batch size from 1024 to 4096 (ablation)embedding-based model · AmazonCat-13KP@1: 94.04 -> 94.21No clear effect
regularization weight lambda 10 vs 1 (ablation)embedding-based model · AmazonCat-13KP@1: 93.68 -> 94.21Improved
GLaS embedding model instead of SLEECembedding-based extreme classification · Amazon-670KPSP@1: 20.62 -> 38.94Improved
GLaS embedding model vs best other methodsextreme classification · Delicious-200K and EURLex-4KP@1: 46.4 vs 47.85 (SLEEC); 77.5 vs 83.83 (PPD-Sparse)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy