IAT: Instance-As-Token Compression for Historical User Sequence Modeling in Industrial Recommender Systems

2026-04-10

AI Summary

This work addresses the limited information capacity of traditional handcrafted sequential features, which constrains recommender system performance. The authors propose IAT, a two-stage sequential modeling framework: first, each historical interaction instance is compressed into a unified instance-level token, supporting both temporal-order and user-order compression strategies; second, fixed-length token sequences are sampled based on timestamps and fed into standard sequential models to capture long-range user preferences. The key innovation lies in enhancing information density through semantically rich instance-level tokens and introducing a user-order alignment mechanism better aligned with downstream tasks. Evaluated across multiple industrial scenarios—including e-commerce advertising, retail marketing, and live-streaming commerce—IAT significantly outperforms existing state-of-the-art methods, achieving substantial gains in key metrics and demonstrating strong cross-domain transferability.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Recommender Systems
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Although sophisticated sequence modeling paradigms have achieved remarkable success in recommender systems, the information capacity of hand-crafted sequential features constrains the performance upper bound. To better enhance user experience by encoding historical interaction patterns, this paper presents a novel two-stage sequence modeling framework termed Instance-As-Token (IAT). The first stage of IAT compresses all features of each historical interaction instance into a unified instance embedding, which encodes the interaction characteristics in a compact yet informative token. Both temporal-order and user-order compression schemes are proposed, with the latter better aligning with the demands of downstream sequence modeling. The second stage involves the downstream task fetching fixed-length compressed instance tokens via timestamps and adopting standard sequence modeling approaches to learn long-range preferences patterns. Extensive experiments demonstrate that IAT significantly outperforms state-of-the-art methods and exhibits superior in-domain and cross-domain transferability. IAT has been successfully deployed in real-world industrial recommender systems, including e-commerce advertising, shopping mall marketing, and live-streaming e-commerce, delivering substantial improvements in key business metrics.

Problem

• sequence modeling
• user historical interactions
• feature compression
• recommender systems
• information capacity

Innovation

• Instance-As-Token
• sequence modeling
• feature compression
• user behavior modeling
• industrial recommender systems