Offline Clustering of Preference Learning with Active-data Augmentation

• URL: http://arxiv.org/abs/2510.26301v2
• Date: Fri, 31 Oct 2025 08:58:46 GMT
• Title: Offline Clustering of Preference Learning with Active-data Augmentation
• Authors: Jingyuan Liu, Fatemeh Ghaffari, Xuchuang Wang, Xutong Liu, Mohammad Hajiesmaili, Carlee Joe-Wong,
• Abstract summary: Real-world preference learning often involves users with different preferences.<n>This setting presents two central challenges: identifying similarity across users to effectively aggregate data, and handling imbalanced offline data.<n>We propose Off-C$2$PL for the pure offline setting, where the learner relies solely on offline data.<n>We extend our framework to the setting with active-data augmentation where the learner is allowed to select a limited number of additional active-data for the test user.
• Score: 32.93090135413931
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Preference learning from pairwise feedback is a widely adopted framework in applications such as reinforcement learning with human feedback and recommendations. In many practical settings, however, user interactions are limited or costly, making offline preference learning necessary. Moreover, real-world preference learning often involves users with different preferences. For example, annotators from different backgrounds may rank the same responses differently. This setting presents two central challenges: (1) identifying similarity across users to effectively aggregate data, especially under scenarios where offline data is imbalanced across dimensions, and (2) handling the imbalanced offline data where some preference dimensions are underrepresented. To address these challenges, we study the Offline Clustering of Preference Learning problem, where the learner has access to fixed datasets from multiple users with potentially different preferences and aims to maximize utility for a test user. To tackle the first challenge, we first propose Off-C$^2$PL for the pure offline setting, where the learner relies solely on offline data. Our theoretical analysis provides a suboptimality bound that explicitly captures the tradeoff between sample noise and bias. To address the second challenge of inbalanced data, we extend our framework to the setting with active-data augmentation where the learner is allowed to select a limited number of additional active-data for the test user based on the cluster structure learned by Off-C$^2$PL. In this setting, our second algorithm, A$^2$-Off-C$^2$PL, actively selects samples that target the least-informative dimensions of the test user's preference. We prove that these actively collected samples contribute more effectively than offline ones. Finally, we validate our theoretical results through simulations on synthetic and real-world datasets.

Related papers

• Offline Clustering of Linear Bandits: The Power of Clusters under Limited Data [60.91600085523719]
  We study the offline clustering of bandits (Off-ClusBand) problem, which studies how to use the offline dataset to learn cluster properties and improve decision-making.<n>We propose two algorithms: Off-C2LUB, which we show analytically and experimentally outperforms existing methods under limited offline user data, and Off-CLUB, which may incur bias when data is sparse but performs well and nearly matches the lower bound when data is sufficient.
  arXiv  Detail & Related papers  (2025-05-25T08:43:40Z)
• A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
  We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts.<n>With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS)<n>Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements.<n>High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
  arXiv  Detail & Related papers  (2024-12-18T15:38:39Z)
• Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning [70.22819290458581]
  Reinforcement learning with human feedback (RLHF) is a widely adopted approach in current large language model pipelines. Our approach introduces two key innovations: (1) on-policy query to avoid OOD and imbalance issues in seed data, and (2) active learning to select the most informative data for preference queries.
  arXiv  Detail & Related papers  (2024-07-02T10:09:19Z)
• Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences [14.686788596611246]
  Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values.<n>Recent alternatives such as Direct Preference Optimization (DPO) simplify this pipeline by directly optimizing on preferences.<n>We propose a theoretical and algorithmic framework for fairness and personalization for diverse users in generative model alignment.
  arXiv  Detail & Related papers  (2024-05-23T21:25:20Z)
• Sample Efficient Preference Alignment in LLMs via Active Exploration [63.84454768573154]
  We take advantage of the fact that one can often choose contexts at which to obtain human feedback to most efficiently identify a good policy.<n>We propose an active exploration algorithm to efficiently select the data and provide theoretical proof that it has a worst-case regret bound.<n>Our method outperforms the baselines with limited samples of human preferences on several language models and four real-world datasets.
  arXiv  Detail & Related papers  (2023-12-01T00:54:02Z)
• Online Coreset Selection for Rehearsal-based Continual Learning [65.85595842458882]
  In continual learning, we store a subset of training examples (coreset) to be replayed later to alleviate catastrophic forgetting. We propose Online Coreset Selection (OCS), a simple yet effective method that selects the most representative and informative coreset at each iteration. Our proposed method maximizes the model's adaptation to a target dataset while selecting high-affinity samples to past tasks, which directly inhibits catastrophic forgetting.
  arXiv  Detail & Related papers  (2021-06-02T11:39:25Z)
• Semi-supervised Collaborative Filtering by Text-enhanced Domain Adaptation [32.93934837792708]
  We consider the problem of recommendation on sparse implicit feedbacks as a semi-supervised learning task. We focus on the most challenging case -- there is no user or item overlap. We adopt domain-invariant textual features as the anchor points to align the latent spaces.
  arXiv  Detail & Related papers  (2020-06-28T05:28:05Z)
• Improving Multi-Turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting [84.9716460244444]
  We consider utilizing the underlying correlation in the data resource itself to derive different kinds of supervision signals. We conduct extensive experiments in two public datasets and obtain significant improvement in both datasets.
  arXiv  Detail & Related papers  (2020-02-18T06:29:01Z)

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.