Enriching Sequential Recommendation with Graph Laplacian Positional Embeddings

2026-09-25

AI Summary

This study addresses the limitation of conventional sequential recommendation systems that rely on ordinal position embeddings, which struggle to capture deep structural relationships among items. We propose a novel paradigm that substitutes ordinal signals with graph-structured signals. Specifically, by constructing an item co-occurrence graph and computing the eigenvectors of its graph Laplacian, we generate frozen positional embeddings that directly replace the learnable embeddings in SASRec while keeping the backbone architecture unchanged. This work is the first to demonstrate that topological item relationships can effectively encode sequential interaction information. Extensive experiments across four benchmark datasets show that the proposed method significantly improves ranking metrics, outperforming multiple strong baselines.

Abstract

Sequential recommenders typically rely on learnable positional embeddings to encode the order of user interactions. In this work, we ask whether this ordinal signal can be replaced by a structural one derived from the item space. We propose to use Laplacian positional embeddings in SASRec: we build an item co-occurrence graph from training interactions, compute eigenvectors of its symmetric normalized Laplacian, and use them as frozen graph-derived positional embeddings. The backbone architecture and training objective remain unchanged. Experiments on four public sequential-recommendation benchmarks show that this simple replacement improves SASRec performance on most ranking metrics and remains competitive with strong positional and temporal encoding baselines. These findings indicate that item-item graph structure can be an effective substitute for standard ordinal positional embeddings in sequential recommendation.

Problem

• Sequential Recommendation
• Positional Embeddings
• Graph Laplacian
• Item Co-occurrence Graph
• Structural Encoding

Innovation

• Sequential Recommendation
• Graph Laplacian
• Positional Embeddings
• Item Co-occurrence Graph
• SASRec