Accurate and Diverse Recommendations via Propensity-Weighted Linear Autoencoders

• URL: http://arxiv.org/abs/2512.20896v1
• Date: Wed, 24 Dec 2025 02:44:25 GMT
• Title: Accurate and Diverse Recommendations via Propensity-Weighted Linear Autoencoders
• Authors: Kazuma Onishi, Katsuhiko Hayashi, Hidetaka Kamigaito,
• Abstract summary: In real-world recommender systems, user-item interactions are Missing Not At Random (MNAR)<n>Inverse Propensity Scoring (IPS) is widely used and commonly models propensities based on a power-law function of item interaction frequency.<n>We address this issue by redefining the propensity score to allow broader item recommendation without excessively penalizing popular items.
• Score: 30.706952059148097
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In real-world recommender systems, user-item interactions are Missing Not At Random (MNAR), as interactions with popular items are more frequently observed than those with less popular ones. Missing observations shift recommendations toward frequently interacted items, which reduces the diversity of the recommendation list. To alleviate this problem, Inverse Propensity Scoring (IPS) is widely used and commonly models propensities based on a power-law function of item interaction frequency. However, we found that such power-law-based correction overly penalizes popular items and harms their recommendation performance. We address this issue by redefining the propensity score to allow broader item recommendation without excessively penalizing popular items. The proposed score is formulated by applying a sigmoid function to the logarithm of the item observation frequency, maintaining the simplicity of power-law scoring while allowing for more flexible adjustment. Furthermore, we incorporate the redefined propensity score into a linear autoencoder model, which tends to favor popular items, and evaluate its effectiveness. Experimental results revealed that our method substantially improves the diversity of items in the recommendation list without sacrificing recommendation accuracy.

Related papers

• Opening the Black Box: Interpretable Remedies for Popularity Bias in Recommender Systems [1.8692254863855962]
  Popularity bias is a well-known challenge in recommender systems, where a small number of popular items receive disproportionate attention.<n>This imbalance often results in reduced recommendation quality and unfair exposure of items.<n>We propose a post-hoc method using a Sparse Autoencoder to interpret and mitigate popularity bias in deep recommendation models.
  arXiv  Detail & Related papers  (2025-08-24T10:59:56Z)
• Balancing Accuracy and Novelty with Sub-Item Popularity [54.56622169534604]
  We propose a novel integration of sub-ID-level personalised popularity within the RecJPQ framework.<n>Our method consistently outperforms item-level PPS by achieving significantly higher personalised novelty without compromising recommendation accuracy.
  arXiv  Detail & Related papers  (2025-08-07T09:33:32Z)
• Repeat-bias-aware Optimization of Beyond-accuracy Metrics for Next Basket Recommendation [54.5376993040561]
  In next basket recommendation (NBR) a set of items is recommended to users based on their historical basket sequences.<n>Some state-of-the-art NBR methods are heavily biased to recommend repeat items so as to maximize utility.<n>We find that only optimizing diversity or item fairness without considering repeat bias may cause NBR algorithms to recommend more repeat items.
  arXiv  Detail & Related papers  (2025-01-10T21:58:34Z)
• Towards Popularity-Aware Recommendation: A Multi-Behavior Enhanced Framework with Orthogonality Constraint [4.137753517504481]
  Top-$K$ recommendation involves inferring latent user preferences and generating personalized recommendations.<n>We present a textbfPopularity-aware top-$K$ recommendation algorithm integrating multi-behavior textbfSide textbfInformation.
  arXiv  Detail & Related papers  (2024-12-26T11:06:49Z)
• Learning Recommender Systems with Soft Target: A Decoupled Perspective [49.83787742587449]
  We propose a novel decoupled soft label optimization framework to consider the objectives as two aspects by leveraging soft labels. We present a sensible soft-label generation algorithm that models a label propagation algorithm to explore users' latent interests in unobserved feedback via neighbors.
  arXiv  Detail & Related papers  (2024-10-09T04:20:15Z)
• Correcting Popularity Bias in Recommender Systems via Item Loss Equalization [1.7771454131646311]
  A small set of popular items dominate the recommendation results due to their high interaction rates.<n>This phenomenon disproportionately benefits users with mainstream tastes while neglecting those with niche interests.<n>We propose an in-processing approach to address this issue by intervening in the training process of recommendation models.
  arXiv  Detail & Related papers  (2024-10-07T08:34:18Z)
• Going Beyond Popularity and Positivity Bias: Correcting for Multifactorial Bias in Recommender Systems [74.47680026838128]
  Two typical forms of bias in user interaction data with recommender systems (RSs) are popularity bias and positivity bias. We consider multifactorial selection bias affected by both item and rating value factors. We propose smoothing and alternating gradient descent techniques to reduce variance and improve the robustness of its optimization.
  arXiv  Detail & Related papers  (2024-04-29T12:18:21Z)
• Improving Recommendation Relevance by simulating User Interest [77.34726150561087]
  We observe that recommendation "recency" can be straightforwardly and transparently maintained by iterative reduction of ranks of inactive items. The basic idea behind this work is patented in a context of online recommendation systems.
  arXiv  Detail & Related papers  (2023-02-03T03:35:28Z)
• Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation [59.500347564280204]
  We propose a new Aleatoric Uncertainty-aware Recommendation (AUR) framework. AUR consists of a new uncertainty estimator along with a normal recommender model. As the chance of mislabeling reflects the potential of a pair, AUR makes recommendations according to the uncertainty.
  arXiv  Detail & Related papers  (2022-09-22T04:32:51Z)
• Unbiased Pairwise Learning to Rank in Recommender Systems [4.058828240864671]
  Unbiased learning to rank algorithms are appealing candidates and have already been applied in many applications with single categorical labels. We propose a novel unbiased LTR algorithm to tackle the challenges, which innovatively models position bias in the pairwise fashion. Experiment results on public benchmark datasets and internal live traffic show the superior results of the proposed method for both categorical and continuous labels.
  arXiv  Detail & Related papers  (2021-11-25T06:04:59Z)
• An Adaptive Boosting Technique to Mitigate Popularity Bias in Recommender System [1.5800354337004194]
  A typical accuracy measure is biased towards popular items, i.e., it promotes better accuracy for popular items compared to non-popular items. This paper considers a metric that measures the popularity bias as the difference in error on popular items and non-popular items. Motivated by the fair boosting algorithm on classification, we propose an algorithm that reduces the popularity bias present in the data.
  arXiv  Detail & Related papers  (2021-09-13T03:04:55Z)

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.