AI Paper Atlas

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

Probabilistic Hash Embeddings for Online Learning of Categorical Features

Aodong Li, Abishek Sankararaman, Balakrishnan Murali Narayanaswamy

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 3 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
replace deterministic hash embeddings with probabilistic hash embeddings and Bayesian online updatesSlowAda hash embedding · Adult online classificationaccuracy (x100): 82.2 -> 84.1Improved
same, vs FastAdaFastAda · Adultaccuracy (x100): 71.1 -> 84.1Improved
same on Retail sequence modelingSlowAda · RetailMAE: 49.1 -> 3.0Improved
same on MovieLens-32MSlowAda · MovieLens-32MMAE (x100): 15.3 -> 14.7Improved
PHE at fixed small memory vs collision-free expandable embeddings P-EEP-EE · RetailMAE: 3.2 -> 3.0Improved
PHE vs collision-free P-EE on AdultP-EE · Adultaccuracy (x100): 84.8 -> 84.1Hurt
PHE vs EE on BankEE · Bankaccuracy (x100): 90.0 -> 89.6No clear effect
more training epochs for deterministic hash embeddings (FastAda)SlowAda · Adultaccuracy (x100): 82.2 -> 71.1Hurt

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