Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-intent-aware Session-based Recommendation

Minjin Choi, Hye-young Kim, Hyunsouk Cho, Jongwuk Lee

TL;DR

This paper tackles the limitation of single-representation session models in session-based recommendation by modeling multiple user intents within a session. It introduces MiaSRec, which uses frequency-aware embeddings, self-attention-based multi-intent representations, and a sparse intent-selection mechanism to adaptively choose relevant intents, followed by decoding and pooling-based aggregation to produce the final recommendations. The approach achieves state-of-the-art results on six real-world datasets, with particularly large gains on longer sessions, demonstrating improved robustness to diverse user intents. The work advances practical SBR by enabling dynamic, intent-aware representations and provides code for reproducibility and wider adoption.

Abstract

Session-based recommendation (SBR) aims to predict the following item a user will interact with during an ongoing session. Most existing SBR models focus on designing sophisticated neural-based encoders to learn a session representation, capturing the relationship among session items. However, they tend to focus on the last item, neglecting diverse user intents that may exist within a session. This limitation leads to significant performance drops, especially for longer sessions. To address this issue, we propose a novel SBR model, called Multi-intent-aware Session-based Recommendation Model (MiaSRec). It adopts frequency embedding vectors indicating the item frequency in session to enhance the information about repeated items. MiaSRec represents various user intents by deriving multiple session representations centered on each item and dynamically selecting the important ones. Extensive experimental results show that MiaSRec outperforms existing state-of-the-art SBR models on six datasets, particularly those with longer average session length, achieving up to 6.27% and 24.56% gains for MRR@20 and Recall@20. Our code is available at https://github.com/jin530/MiaSRec.

Multi-intent-aware Session-based Recommendation

TL;DR

This paper tackles the limitation of single-representation session models in session-based recommendation by modeling multiple user intents within a session. It introduces MiaSRec, which uses frequency-aware embeddings, self-attention-based multi-intent representations, and a sparse intent-selection mechanism to adaptively choose relevant intents, followed by decoding and pooling-based aggregation to produce the final recommendations. The approach achieves state-of-the-art results on six real-world datasets, with particularly large gains on longer sessions, demonstrating improved robustness to diverse user intents. The work advances practical SBR by enabling dynamic, intent-aware representations and provides code for reproducibility and wider adoption.

Abstract

Session-based recommendation (SBR) aims to predict the following item a user will interact with during an ongoing session. Most existing SBR models focus on designing sophisticated neural-based encoders to learn a session representation, capturing the relationship among session items. However, they tend to focus on the last item, neglecting diverse user intents that may exist within a session. This limitation leads to significant performance drops, especially for longer sessions. To address this issue, we propose a novel SBR model, called Multi-intent-aware Session-based Recommendation Model (MiaSRec). It adopts frequency embedding vectors indicating the item frequency in session to enhance the information about repeated items. MiaSRec represents various user intents by deriving multiple session representations centered on each item and dynamically selecting the important ones. Extensive experimental results show that MiaSRec outperforms existing state-of-the-art SBR models on six datasets, particularly those with longer average session length, achieving up to 6.27% and 24.56% gains for MRR@20 and Recall@20. Our code is available at https://github.com/jin530/MiaSRec.
Paper Structure (12 sections, 8 equations, 3 figures, 3 tables)

This paper contains 12 sections, 8 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Proposed Model
  3. Session-based Recommendation
  4. Model Architecture
  5. Embedding Layer
  6. Multi-intent Representation
  7. Intent Selection
  8. Multi-intent Aggregation
  9. Experiments
  10. Experimental Setup
  11. Experimental Results
  12. Conclusion

Figures (3)

  • Figure 1: A session example with multiple user intents, such as travel, fashion, sun protection, and photo. Dotted rectangles represent items related to each user intent, and solid rectangles represent recommendations for each user intent.
  • Figure 2: The model architecture of MiaSRec.
  • Figure 3: Performance comparison of SBR models over varying session lengths. Sessions are divided into six groups depending on session length.