PreDiff: Sequential Recommendation by Denoising Preference Distributions

Sequential recommendation predicts which item a user will interact with next. A key property of this task is that user preferences are concentrated: only a small cluster of items is relevant at a given moment. Recent diffusion-based methods add noise to the item's embedding and score candidates by embedding similarity. Since similar items have similar embeddings, their score gaps are inherently small and easily overwhelmed by noise, causing the most relevant candidates to become indistinguishable first. We prove that moving diffusion to distribution space, where each item receives independent noise, preserves rankings better and makes the reverse denoising process easier. This shift, however, loses the semantic structure of embedding space and requires richer supervision than one-hot labels. We propose PreDiff (**Pre**ference **Diff**usion), which performs diffusion in distribution space and introduces two components to address these problems: Distribution-Guided Sparse Projection projects the preference scores into embedding space while filtering out low-relevance noise, and soft targets encode inter-item similarity to teach fine-grained ranking within the preference cluster. On four benchmarks, PreDiff achieves 8%–17% relative improvement over existing methods.