Learning Behaviorally Grounded Item Embeddings via Personalized Temporal Contexts

• URL: http://arxiv.org/abs/2604.15581v1
• Date: Thu, 16 Apr 2026 23:28:27 GMT
• Title: Learning Behaviorally Grounded Item Embeddings via Personalized Temporal Contexts
• Abstract summary: We introduce TAI2Vec (Time-Aware Item-to-SID), a family of lightweight embedding models that integrates temporal proximity directly into the representation process.<n>We show that TAI2Vec consistently produces more accurate and behaviorally grounded representations than static baselines, achieving competitive or superior performance in over 80% of the datasets.
• Score: 1.4174475093445233
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Effective user modeling requires distinguishing between short-term and long-term preference evolution. While item embeddings have become a key component of recommender systems, standard approaches like Item2Vec treat user histories as unordered sets (bag-of-items), implicitly assuming that interactions separated by minutes are as semantically related as those separated by months. This simplification flattens the rich temporal structure of user behavior, obscuring the distinction between coherent consumption sessions and gradual interest drifts. In this work, we introduce TAI2Vec (Time-Aware Item-to-Vector), a family of lightweight embedding models that integrates temporal proximity directly into the representation learning process. Unlike approaches that apply global time constraints, TAI2Vec is user-adaptive, tailoring its temporal definitions to individual interaction paces. We propose two complementary strategies: TAI2Vec-Disc, which utilizes personalized anomaly detection to dynamically segment interactions into semantic sessions, and TAI2Vec-Cont, which employs continuous, user-specific decay functions to weigh item relationships based on their relative temporal distance. Experimental results across eight diverse datasets demonstrate that TAI2Vec consistently produces more accurate and behaviorally grounded representations than static baselines, achieving competitive or superior performance in over 80% of the datasets, with improvements of up to 135%. The source code is publicly available at https://github.com/UFSCar-LaSID/tai2vec.

Related papers

• S2-CAR: Segmentation-Supervised Complexity-Adaptive Recommendation [11.19507489603123]
  We propose S2-CAR, a segmentation-supervised framework for sequential recommendation that models user intent as a continuous latent energy state.<n> Specifically, it uses the Context-Aware Soft Temporal Point Process (Soft-TPP) to segment boundaries triggered by the natural decay of latent-state energy rather than fixed intervals.<n>Further analysis shows that the proposed energy-based segmentation serves as a plug-and-play module, yielding consistent improvements when integrated into existing sequential recommendation backbones.
  arXiv  Detail & Related papers  (2026-06-24T05:24:18Z)
• PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments [72.02445514666428]
  We introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall.<n>PerMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time.<n> Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption.
  arXiv  Detail & Related papers  (2026-03-24T14:04:11Z)
• A theoretical framework for self-supervised contrastive learning for continuous dependent data [79.62732169706054]
  Self-supervised learning (SSL) has emerged as a powerful approach to learning representations, particularly in the field of computer vision.<n>We propose a novel theoretical framework for contrastive SSL tailored to emphsemantic independence between samples.<n>Specifically, we outperform TS2Vec on the standard UEA and UCR benchmarks, with accuracy improvements of $4.17$% and $2.08$%, respectively.
  arXiv  Detail & Related papers  (2025-06-11T14:23:47Z)
• FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification [56.925103708982164]
  We present a novel perspective from the frequency domain and identify three advantages for downstream classification: global, independent, and compact.<n>We propose the lightweight yet effective Frequency Refined Augmentation (FreRA) tailored for time series contrastive learning on classification tasks.<n>FreRA consistently outperforms ten leading baselines on time series classification, anomaly detection, and transfer learning tasks.
  arXiv  Detail & Related papers  (2025-05-29T07:18:28Z)
• Sequential Recommendation on Temporal Proximities with Contrastive Learning and Self-Attention [3.7182810519704095]
  Sequential recommender systems identify user preferences from their past interactions to predict subsequent items optimally. Recent models often neglect similarities in users' actions that occur implicitly among users during analogous timeframes. We propose a sequential recommendation model called TemProxRec, which includes contrastive learning and self-attention methods to consider temporal proximities.
  arXiv  Detail & Related papers  (2024-02-15T08:33:16Z)
• Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning [35.27714529976667]
  Temporal relation classification is a pair-wise task for identifying the relation of a temporal link (Tlink) between two mentions. This paper presents an event centric model that allows to manage dynamic event representations across multiple Tlink categories. Our proposal outperforms state-of-the-art models and two transfer learning baselines on both the English and Japanese data.
  arXiv  Detail & Related papers  (2023-10-31T07:41:24Z)
• Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition [88.34182299496074]
  Action labels are only available on a source dataset, but unavailable on a target dataset in the training stage. We utilize a self-supervision scheme to reduce the domain shift between two skeleton-based action datasets. By segmenting and permuting temporal segments or human body parts, we design two self-supervised learning classification tasks.
  arXiv  Detail & Related papers  (2022-07-17T07:05:39Z)
• Multi-Behavior Sequential Recommendation with Temporal Graph Transformer [66.10169268762014]
  We tackle the dynamic user-item relation learning with the awareness of multi-behavior interactive patterns. We propose a new Temporal Graph Transformer (TGT) recommendation framework to jointly capture dynamic short-term and long-range user-item interactive patterns.
  arXiv  Detail & Related papers  (2022-06-06T15:42:54Z)
• Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation [62.30552176649873]
  We devise a novel Dynamic Representation Learning model for Sequential Recommendation (DRL-SRe) To better model the user-item interactions for characterizing the dynamics from both sides, the proposed model builds a global user-item interaction graph for each time slice. To enable the model to capture fine-grained temporal information, we propose an auxiliary temporal prediction task over consecutive time slices.
  arXiv  Detail & Related papers  (2021-09-24T07:44:27Z)
• Dynamic Embeddings for Interaction Prediction [2.5758502140236024]
  In recommender systems (RSs), predicting the next item that a user interacts with is critical for user retention. Recent studies have shown the effectiveness of modeling the mutual interactions between users and items using separate user and item embeddings. We propose a novel method called DeePRed that addresses some of their limitations.
  arXiv  Detail & Related papers  (2020-11-10T16:04:46Z)

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.