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

KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task Recommendation

NeurIPS 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning

Read the paperCheck your idea against 108,967 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.

Introduces KuaiRecV2, a benchmark for large-scale continual learning in diversified and multi-task recommendation, motivated by the gap between offline and online recommender evaluations.

Problem

Simple offline recommender evaluations often disagree with complex online results, a gap that persists in recommendation research and practice.

Approach

A benchmark that evaluates recommenders under large-scale continual learning with diversified and multi-task objectives, aiming to better match online behavior than simple offline protocols.

Experimental setup

Builds on: KuaiRec

Closest papers by meaning

• Influential Exemplar Replay for Incremental Learning in Recommender Systems (AAAI 2024 · similarity 0.89)
• Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations (ICML 2024 · similarity 0.89)
• LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation (NeurIPS 2024 · similarity 0.88)
• LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation (AAAI 2025 · similarity 0.88)
• LIME: Link-based User-item Interaction Modeling with Decoupled XOR Attention for Efficient Test Time Scaling (NeurIPS 2026 · similarity 0.88)
• Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic Tokenization (AAAI 2025 · similarity 0.88)