English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Multi-Behavior Sequential Transformer Recommender (MB-STR) — SIGIR Paper

Forum topic · 小凯 · 2026-07-05

Summary

This forum entry indexes the paper "Multi-Behavior Sequential Transformer Recommender" published at SIGIR, available via ACM Digital Library at https://dl.acm.org/doi/abs/10.1145/3477495.3532023. The work belongs to the sequential recommendation field and addresses the challenge that users on e-commerce and content platforms generate multiple types of behaviors (such as clicks, adding to cart, and purchases), each carrying different intent signals. Rather than treating all interactions uniformly, the approach models heterogeneous behavior types within a Transformer-based sequential recommendation framework, aiming to better capture user intent from multi-behavior sequences. The post situates the paper in the broader evolution of sequential recommendation research—alongside methods like BERT4Rec, Mamba4Rec, EAGER, and P5—and outlines the standard research pipeline: problem formulation, model and system design, training procedures, and inference strategies. It also discusses evaluation practice with common metrics (nDCG, Recall@k, Hit@k), datasets, and baselines, and lists open challenges including evaluation reliability, latency and cost, and cross-domain generalization. Readers should consult the original PDF for exact quantitative results.

Multi-Behavior Sequential Transformer Recommender (SIGIR)

Metadata

| Field | Content | |------|------| | Title | Multi-Behavior Sequential Transformer Recommender | | Venue | SIGIR | | Source link | https://dl.acm.org/doi/abs/10.1145/3477495.3532023 | | Resource type | Academic paper | | Category | Sequential Recommendation |

Overview

This entry indexes a SIGIR paper on multi-behavior sequential recommendation. In large-scale recommender systems, users do not interact with items in a single way: a typical e-commerce session mixes clicks, adding items to carts, favoriting, and purchases. These heterogeneous behavior types carry different signals about user intent and have different levels of commitment. The paper proposes a Transformer-based sequential recommendation approach that explicitly takes multiple behavior types into account when modeling user interaction sequences, aiming to improve next-item prediction over methods that flatten all behaviors into a single stream.

Problem Setting and Motivation

Sequential recommendation has long faced challenges around user-intent understanding, efficiency, and scalability. Classic pipelines treat retrieval, ranking, and generation separately, and standard sequential models (e.g., session-based Transformers) often ignore *which type* of behavior occurred, focusing only on the ordered list of item IDs. Multi-behavior modeling tries to recover the richer intent structure behind the sequence:

  • Different behaviors imply different interest strengths (a purchase is stronger evidence than a click);
  • Behavior order and type transitions encode short-term intent;
  • Single-behavior data (purchase only) is typically sparse, while clicks are abundant but noisy.
  • Method Outline

    Following the standard pipeline for this line of work:

    1. Input and representation: encode user interaction sequences of items together with their behavior-type labels; 2. Core module: a Transformer backbone processes the combined item–behavior sequence; 3. Learning strategy: training on behavior-aware next-item prediction over logged user sequences; 4. Inference: score candidate items from the final sequence representation.

    For the precise architecture details, loss design, and hyperparameters, refer to the original PDF at the ACM link above — this post is an index entry, and quantitative claims should be verified against the paper itself.

    Evaluation Practice

    Papers in this area are typically evaluated with:

  • Datasets: public recommendation datasets containing multiple behavior types;
  • Metrics: Recall@k, Hit@k, nDCG@k;
  • Baselines: single-behavior sequential recommenders and other multi-behavior methods;
  • Ablations: contribution of behavior-type modeling versus sequence modeling alone.
  • Key Takeaways for Search / Rec / Personalization

    1. Architecture: behavior-aware sequence encoders remain a strong baseline family; the trend is toward generative and LLM-based recommenders, but heterogeneous behavior signals are still crucial supervision; 2. Data: interaction logs of different behavior types are the key asset; filtering and type alignment matter; 3. Evaluation: offline ranking metrics should be cross-checked against online satisfaction metrics; 4. Deployment: latency, cost, and interpretability constraints remain hard requirements in production.

    Limitations and Future Directions

    Likely limitations include benchmark–reality distribution mismatch, sparse behavior labels, and unknown cross-domain generalization. Future work can explore deeper integration with knowledge graphs, causal and fairness constraints, and generative recommendation over multi-behavior logs.

    Related Entries

  • BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations
  • EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration
  • Efficient On-Device Session-Based Recommendation
  • How to Index Item IDs for Recommendation Foundation Models (P5, SIGIR)
  • LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models
  • Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models
  • Reference

  • Original paper: *Multi-Behavior Sequential Transformer Recommender*, SIGIR. DOI link: <https://dl.acm.org/doi/abs/10.1145/3477495.3532023>

Tags

#sequential-recommendation#multi-behavior#transformer#sigir#recommender-systems#user-behavior-modeling

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208984