SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation

• URL: http://arxiv.org/abs/2608.03692v1
• Date: Tue, 04 Aug 2026 13:59:44 GMT
• Title: SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation
• Abstract summary: We propose textbfSITA, a target-aware compression framework for long-sequence recommendation.<n>SITA adaptively aggregates the corresponding structured interests to construct the target-specific user representation.<n>Experiments on public datasets and a large-scale industrial dataset demonstrate that SITA consistently outperforms representative baselines.
• Score: 69.02976266748193
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As user behavior histories continue to grow on modern Internet platforms, effectively modeling long behavior sequences has become crucial for predicting user interests in candidate items. Existing methods have evolved along two directions. One line dynamically retrieves target-relevant behaviors from long histories, enabling target-aware modeling but requiring target-dependent computation during inference. The other line compresses entire behavior sequences into compact user representations, achieving high efficiency and scalability but sacrificing target-specific adaptation due to target-independent encoding. The key challenge is therefore to enable target-aware modeling while preserving the efficiency and scalability of compressed user representations. To address this challenge, we propose \textbf{SITA}, a target-aware compression framework for long-sequence recommendation. SITA enables target-aware compression by organizing compressed interests into semantic structures through semantic identifiers learned via parallel semantic quantization. Conditioned on the semantic identifier of the target item, SITA adaptively aggregates the corresponding structured interests to construct the target-specific user representation. Extensive experiments on public datasets and a large-scale industrial dataset demonstrate that SITA consistently outperforms representative baselines while maintaining strong scalability, highlighting its strong potential for real-world recommender systems.

Related papers

• STAR: Structured Tokenization and Target-Aware Interest Representation for PCVR Prediction [7.574291100593417]
  We present STAR (Structured Tokenization and Target-Aware Interest Representation), a framework for the KDD Cup 2026 Tencent UniRec Challenge.<n> STAR combines structured feature tokenization with target-aware interest representation on top of a HyFormer-style multi-sequence backbone.<n> Experiments on the challenge dataset identify the components that most reliably improve ranking AUC, while LogLoss is reported as a calibration diagnostic.
  arXiv  Detail & Related papers  (2026-08-13T09:09:54Z)
• Collaborative Memory Augmentation for Generative Recommendation [49.76630658239287]
  We propose textbfOMEGA, a cOllaborative MEmory augmentation framework for Generative recommendAtion.<n>We first introduce a latent context compression method that utilizes learnable query tokens to distill sequential user behavior into compact representations.<n>These compressed representations are aggregated into a collaborative memory bank, serving as an explicit repository of global behavioral patterns.
  arXiv  Detail & Related papers  (2026-08-02T15:34:43Z)
• Behavior-Aware Dual-Channel Preference Learning for Heterogeneous Sequential Recommendation [18.573543141847317]
  Heterogeneous sequential recommendation (HSR) aims to learn dynamic behavior dependencies from the diverse behaviors of user-item interactions to facilitate precise sequential recommendation.<n>One significant issue is the inherent sparsity of a real-world data, which can weaken the recommendation performance.<n>We have meticulously designed a behavior-aware dual-channel preference learning framework.
  arXiv  Detail & Related papers  (2026-04-16T03:20:11Z)
• HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders [13.73393292649997]
  We propose HiSAC, an efficient framework for personalized sequence modeling.<n>HiSAC encodes interactions into multi-level semantic IDs and constructs a global hierarchical codebook.<n>A hierarchical voting mechanism sparsely activates personalized interest-agents as fine-grained preference centers.<n>Soft-Routing Attention aggregates historical signals in semantic space, weighting by similarity to minimize quantization error.
  arXiv  Detail & Related papers  (2026-02-24T15:28:58Z)
• CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension [49.6969505536365]
  We propose CREM, with a unified framework that enhances multimodal representations for retrieval while preserving generative ability.<n>CREM achieves state-of-the-art retrieval performance on MMEB while maintaining strong generative performance on multiple comprehension benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T08:09:51Z)
• GEMs: Breaking the Long-Sequence Barrier in Generative Recommendation with a Multi-Stream Decoder [54.64137490632567]
  We propose a novel and unified framework designed to capture users' sequences from long-term history.<n>Generative Multi-streamers ( GEMs) break user sequences into three streams.<n>Extensive experiments on large-scale industrial datasets demonstrate that GEMs significantly outperforms state-the-art methods in recommendation accuracy.
  arXiv  Detail & Related papers  (2026-02-14T06:42:56Z)
• Unleash the Potential of Long Semantic IDs for Generative Recommendation [5.6264583086973685]
  ACERec is a novel framework that decouples the gap between fine-grained tokenization and efficient sequential modeling.<n>It consistently outperforms state-of-the-art baselines on six real-world benchmarks.
  arXiv  Detail & Related papers  (2026-02-14T03:15:31Z)
• GLASS: A Generative Recommender for Long-sequence Modeling via SID-Tier and Semantic Search [51.44490997013772]
  GLASS is a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search.<n>We show that GLASS outperforms state-of-the-art baselines in experiments on two large-scale real-world datasets.
  arXiv  Detail & Related papers  (2026-02-05T13:48:33Z)
• Unleashing the Potential of Sparse Attention on Long-term Behaviors for CTR Prediction [17.78352301235849]
  We propose SparseCTR, an efficient and effective model specifically designed for long-term behaviors of users.<n>Based on these chunks, we propose a three-branch sparse self-attention mechanism to jointly identify users' global interests.<n>We show that SparseCTR not only improves efficiency but also outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-01-25T13:39:26Z)
• ENCODE: Breaking the Trade-Off Between Performance and Efficiency in Long-Term User Behavior Modeling [12.963611514800656]
  We propose an efficient two-stage long-term sequence modeling approach, named as EfficieNt Clustering based twO-stage interest moDEling (ENCODE)<n>In the offline extraction stage, ENCODE clusters the entire behavior sequence and extracts accurate interests.<n>While in the online inference stage, ENCODE takes the off-the-shelf user interests to predict the associations with target items.
  arXiv  Detail & Related papers  (2025-08-19T06:58:21Z)
• Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation [102.24108167002252]
  We propose a novel attention network, named self-modulating attention, that models the complex and non-linearly evolving dynamic user preferences. We empirically demonstrate the effectiveness of our method on top-N sequential recommendation tasks, and the results on three large-scale real-world datasets show that our model can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-03-30T03:54:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.