From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation

• URL: http://arxiv.org/abs/2509.23649v1
• Date: Sun, 28 Sep 2025 05:22:19 GMT
• Title: From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
• Authors: KaiWen Wei, Kejun He, Xiaomian Kang, Jie Zhang, Yuming Yang, Jiang Zhong, He Bai, Junnan Zhu,
• Abstract summary: Masked History Learning (MHL) is a novel training framework that shifts the objective from simple next-step prediction to deep comprehension of history.<n>MHL augments the standard autoregressive objective with an auxiliary task of reconstructing masked historical items.<n> Experiments on three public datasets show that our method significantly outperforms state-of-the-art generative models.
• Score: 25.25652053392233
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative recommendation, which directly generates item identifiers, has emerged as a promising paradigm for recommendation systems. However, its potential is fundamentally constrained by the reliance on purely autoregressive training. This approach focuses solely on predicting the next item while ignoring the rich internal structure of a user's interaction history, thus failing to grasp the underlying intent. To address this limitation, we propose Masked History Learning (MHL), a novel training framework that shifts the objective from simple next-step prediction to deep comprehension of history. MHL augments the standard autoregressive objective with an auxiliary task of reconstructing masked historical items, compelling the model to understand ``why'' an item path is formed from the user's past behaviors, rather than just ``what'' item comes next. We introduce two key contributions to enhance this framework: (1) an entropy-guided masking policy that intelligently targets the most informative historical items for reconstruction, and (2) a curriculum learning scheduler that progressively transitions from history reconstruction to future prediction. Experiments on three public datasets show that our method significantly outperforms state-of-the-art generative models, highlighting that a comprehensive understanding of the past is crucial for accurately predicting a user's future path. The code will be released to the public.

Related papers

• GenCI: Generative Modeling of User Interest Shift via Cohort-based Intent Learning for CTR Prediction [84.0125708499372]
  We propose a generative user intent framework to model user preferences for click-through rate (CTR) prediction.<n>The framework first employs a generative model, trained with a next-item prediction objective, to proactively produce candidate interest cohorts.<n>A hierarchical candidate-aware network then injects this rich contextual signal into the ranking stage, refining them with cross-attention to align with both user history and the target item.
  arXiv  Detail & Related papers  (2026-01-26T08:15:04Z)
• Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking [27.82131411594034]
  Leveraging the session context has proven to be beneficial for inferring user search intent and document ranking.<n>Despite these advances, the limitation of historical session data for capturing evolving user intent remains a challenge.<n>We present the siamese model optimization framework, comprising a history-conditioned model and a future-aware model.
  arXiv  Detail & Related papers  (2025-05-20T10:36:25Z)
• Slow Thinking for Sequential Recommendation [88.46598279655575]
  We present a novel slow thinking recommendation model, named STREAM-Rec.<n>Our approach is capable of analyzing historical user behavior, generating a multi-step, deliberative reasoning process, and delivering personalized recommendations.<n>In particular, we focus on two key challenges: (1) identifying the suitable reasoning patterns in recommender systems, and (2) exploring how to effectively stimulate the reasoning capabilities of traditional recommenders.
  arXiv  Detail & Related papers  (2025-04-13T15:53:30Z)
• Dense Policy: Bidirectional Autoregressive Learning of Actions [51.60428100831717]
  This paper introduces a bidirectionally expanded learning approach, termed Dense Policy, to establish a new paradigm for autoregressive policies in action prediction.<n>It employs a lightweight encoder-only architecture to iteratively unfold the action sequence from an initial single frame into the target sequence in a coarse-to-fine manner.<n>Experiments validate that our dense policy has superior autoregressive learning capabilities and can surpass existing holistic generative policies.
  arXiv  Detail & Related papers  (2025-03-17T14:28:08Z)
• Generative Regression Based Watch Time Prediction for Short-Video Recommendation [36.95095097454143]
  Watch time prediction has emerged as a pivotal task in short video recommendation systems.<n>Recent studies have attempted to address these issues by converting the continuous watch time estimation into an ordinal regression task.<n>We propose a novel Generative Regression (GR) framework that reformulates WTP as a sequence generation task.
  arXiv  Detail & Related papers  (2024-12-28T16:48:55Z)
• GenRec: Generative Sequential Recommendation with Large Language Models [4.381277509913139]
  We propose a novel model named Generative Recommendation (GenRec) GenRec is lightweight and requires only a few hours to train effectively in low-resource settings. Our experiments have demonstrated that GenRec generalizes on various public real-world datasets.
  arXiv  Detail & Related papers  (2024-07-30T20:58:36Z)
• Active Exploration via Autoregressive Generation of Missing Data [11.713451719120707]
  We pose uncertainty quantification and exploration in online decision-making as a problem of training and generation from an autoregressive sequence model.<n>Our approach rests on viewing uncertainty as arising from missing future outcomes that would be revealed through appropriate action choices.
  arXiv  Detail & Related papers  (2024-05-29T19:24:44Z)
• Look into the Future: Deep Contextualized Sequential Recommendation [28.726897673576865]
  We propose a novel framework of sequential recommendation called Look into the Future (LIFT) LIFT builds and leverages the contexts of sequential recommendation. In our experiments, LIFT achieves significant performance improvement on click-through rate prediction and rating prediction tasks.
  arXiv  Detail & Related papers  (2024-05-23T09:34:28Z)
• HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph [14.832067253514213]
  We propose the Historical Information Passing (HIP) network to predict future events. Our method considers the updating of relation representations and adopts three scoring functions corresponding to the above dimensions. Experimental results on five benchmark datasets show the superiority of HIP network.
  arXiv  Detail & Related papers  (2024-02-19T11:50:30Z)
• Continual Zero-Shot Learning through Semantically Guided Generative Random Walks [56.65465792750822]
  We address the challenge of continual zero-shot learning where unseen information is not provided during training, by leveraging generative modeling. We propose our learning algorithm that employs a novel semantically guided Generative Random Walk (GRW) loss. Our algorithm achieves state-of-the-art performance on AWA1, AWA2, CUB, and SUN datasets, surpassing existing CZSL methods by 3-7%.
  arXiv  Detail & Related papers  (2023-08-23T18:10:12Z)
• Learning to Rank in Generative Retrieval [62.91492903161522]
  Generative retrieval aims to generate identifier strings of relevant passages as the retrieval target. We propose a learning-to-rank framework for generative retrieval, dubbed LTRGR. This framework only requires an additional learning-to-rank training phase to enhance current generative retrieval systems.
  arXiv  Detail & Related papers  (2023-06-27T05:48:14Z)
• Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment [72.50906475214457]
  The goal of sequential event prediction is to estimate the next event based on a sequence of historical events. In practice, the next-event prediction models are trained with sequential data collected at one time. We propose a framework with hierarchical branching structures for learning context-specific representations.
  arXiv  Detail & Related papers  (2022-10-24T07:54:13Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

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.