Enhancing guidance for missing data in diffusion-based sequential recommendation

2026-01-22

AI Summary

Missing data often obscures critical interest shifts in user interaction sequences, thereby degrading the quality of guidance signals for diffusion-based recommendation models. To address this issue, this work proposes CARD, a novel framework that explicitly identifies significant interest transitions by leveraging bilateral Thompson sampling to detect turning points. CARD further introduces a counterfactual attention mechanism that dynamically reweights interaction embeddings to generate high-quality guidance signals for the diffusion process. Extensive experiments on multiple real-world datasets demonstrate that CARD substantially improves recommendation performance while maintaining low computational overhead, offering both effectiveness and practicality.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Computer Vision: Diffusion Models for Vision
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Contemporary sequential recommendation methods are becoming more complex, shifting from classification to a diffusion-guided generative paradigm. However, the quality of guidance in the form of user information is often compromised by missing data in the observed sequences, leading to suboptimal generation quality. Existing methods address this by removing locally similar items, but overlook ``critical turning points''in user interest, which are crucial for accurately predicting subsequent user intent. To address this, we propose a novel Counterfactual Attention Regulation Diffusion model (CARD), which focuses on amplifying the signal from key interest-turning-point items while concurrently identifying and suppressing noise within the user sequence. CARD consists of (1) a Dual-side Thompson Sampling method to identify sequences undergoing significant interest shift, and (2) a counterfactual attention mechanism for these sequences to quantify the importance of each item. In this manner, CARD provides the diffusion model with a high-quality guidance signal composed of dynamically re-weighted interaction vectors to enable effective generation. Experiments show our method works well on real-world data without being computationally expensive. Our code is available at https://github.com/yanqilong3321/CARD.

Problem

• missing data
• sequential recommendation
• diffusion model
• user interest shift
• guidance quality

Innovation

• diffusion-based recommendation
• counterfactual attention
• interest turning point
• missing data guidance
• Thompson sampling