**arXiv ID:** 2306.12619 **Authors:** Yijia Shao, Yiduo Guo, Dongyan Zhao, Bing Liu **Published:** 2023-06-22T01:14:47Z **Abstract:** Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) setting due to catastrophic forgetting (CF). This paper reports our finding that if we formulate CIL as a continual label generation problem, CF is drastically reduced and the generaliz...
Scanned 9/11/2026
Install to Claude Code
Skills Directorynpx -y skills add hiyenwong/ai_collection --skill classincremental-learning-based-on-label-generation --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Classincremental Learning Based On Label Generation?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-classincremental-learning-based-on-label-generatio)More formats (shields.io, HTML) on the badges page.
# Class-Incremental Learning based on Label Generation
**arXiv ID:** 2306.12619
**Authors:** Yijia Shao, Yiduo Guo, Dongyan Zhao, Bing Liu
**Published:** 2023-06-22T01:14:47Z
**Abstract:**
Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) setting due to catastrophic forgetting (CF). This paper reports our finding that if we formulate CIL as a continual label generation problem, CF is drastically reduced and the generalizable representations of pre-trained models can be better retained. We thus propose a new CIL method (VAG) that also leverages the sparsity of vocabulary to focus the generation and creates pseudo-replay samples by using label semantics. Experimental results show that VAG outperforms baselines by a large margin.
## Skill Description
This skill is generated from the arXiv paper: Class-Incremental Learning based on Label Generation (2306.12619).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2306.12619](http://arxiv.org/abs/2306.12619v2)
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review...
Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publi...
Semantic search, similar content discovery, and structured research using Exa API
