AI Paper Atlas

Research map / Continual learning / Class-incremental

TailAdapt: Heavy-Tailed Sparse Variational Adaptation for Long-Tailed Class Incremental Learning

Abhishek Kumar Sinha, Nitant Dube, Soma Biswas

NeurIPS 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes TailAdapt, a heavy-tailed sparse variational adaptation method for long-tailed class-incremental learning that addresses asymmetric likelihood signals between head and tail classes.

Problem

Long-tailed class-incremental learning (LT-CIL), where severe class imbalance lets head classes dominate gradient updates and tail classes stay near the prior mean because they contribute insufficient likelihood evidence within each session.

Approach

Identifies an asymmetry in per-session likelihood signals between head and tail classes and uses heavy-tailed sparse variational adaptation to counter prior regularization suppressing tail-class parameters. Details beyond the abstract are not available.

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