Handling Large-scale Cardinality in building recommendation systems

• URL: http://arxiv.org/abs/2401.09572v1
• Date: Wed, 17 Jan 2024 19:49:11 GMT
• Title: Handling Large-scale Cardinality in building recommendation systems
• Authors: Dhruva Dixith Kurra, Bo Ling, Chun Zh, Seyedshahin Ashrafzadeh
• Abstract summary: This paper presents two innovative techniques to address the challenge of high cardinality in recommendation systems. We propose a bag-of-words approach, combined with layer sharing, to substantially decrease the model size while improving performance.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Effective recommendation systems rely on capturing user preferences, often requiring incorporating numerous features such as universally unique identifiers (UUIDs) of entities. However, the exceptionally high cardinality of UUIDs poses a significant challenge in terms of model degradation and increased model size due to sparsity. This paper presents two innovative techniques to address the challenge of high cardinality in recommendation systems. Specifically, we propose a bag-of-words approach, combined with layer sharing, to substantially decrease the model size while improving performance. Our techniques were evaluated through offline and online experiments on Uber use cases, resulting in promising results demonstrating our approach's effectiveness in optimizing recommendation systems and enhancing their overall performance.

Related papers

• Slow Thinking for Sequential Recommendation [88.46598279655575]
  We present a novel slow thinking recommendation model, named STREAM-Rec. Our approach is capable of analyzing historical user behavior, generating a multi-step, deliberative reasoning process, and delivering personalized recommendations. 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)
• Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection [71.92083784393418]
  Inference-time methods such as Best-of-N (BON) sampling offer a simple yet effective alternative to improve performance. We propose Iterative Agent Decoding (IAD) which combines iterative refinement with dynamic candidate evaluation and selection guided by a verifier.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)
• Enhancing Healthcare Recommendation Systems with a Multimodal LLMs-based MOE Architecture [4.429093762434193]
  We build a small dataset for recommending healthy food based on patient descriptions. We evaluate the model's performance on several key metrics, including Precision, Recall, NDCG, and MAP@5. The paper finds image data provided relatively limited improvement in the performance of the personalized recommendation system.
  arXiv  Detail & Related papers  (2024-12-16T08:42:43Z)
• AltFS: Agency-light Feature Selection with Large Language Models in Deep Recommender Systems [43.279297619296635]
  We propose AltFS, an Agency-light Feature Selection method for deep recommender systems. In this paper, we propose AltFS, an Agency-light Feature Selection method for deep recommender systems.
  arXiv  Detail & Related papers  (2024-12-11T16:28:18Z)
• Efficient and Robust Regularized Federated Recommendation [52.24782464815489]
  The recommender system (RSRS) addresses both user preference and privacy concerns. We propose a novel method that incorporates non-uniform gradient descent to improve communication efficiency. RFRecF's superior robustness compared to diverse baselines.
  arXiv  Detail & Related papers  (2024-11-03T12:10:20Z)
• 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)
• Counterfactual Evaluation of Ads Ranking Models through Domain Adaptation [4.488611783089895]
  This approach measures reward for ranking model changes in large-scale Ads recommender systems. Our experiments demonstrate that the proposed technique outperforms both the vanilla IPS method and approaches using non-generalized reward models.
  arXiv  Detail & Related papers  (2024-09-29T23:12:04Z)
• LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation [15.972926854420619]
  Leveraging large language models (LLMs) offers new opportunities for comprehensive recommendation logic generation. Fine-tuning LLM models for recommendation tasks incurs high computational costs and alignment issues with existing systems. In this work, our proposed effective strategy LANE aligns LLMs with online recommendation systems without additional LLMs tuning.
  arXiv  Detail & Related papers  (2024-07-03T06:20:31Z)
• Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance [59.71186244597394]
  We introduce an effective approach to stabilize the proposal-target matching in point-based methods. We propose Auxiliary Point Guidance (APG) to provide clear and effective guidance for proposal selection and optimization. We also develop Implicit Feature Interpolation (IFI) to enable adaptive feature extraction in diverse crowd scenarios.
  arXiv  Detail & Related papers  (2024-05-17T07:23:27Z)
• Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly [79.07074710460012]
  adversarial vulnerability of deep neural networks (DNNs) has drawn great attention. An increasing number of transfer-based methods have been developed to fool black-box DNN models. We establish a transfer-based attack benchmark (TA-Bench) which implements 30+ methods.
  arXiv  Detail & Related papers  (2023-11-02T15:35:58Z)
• Fisher-Weighted Merge of Contrastive Learning Models in Sequential Recommendation [0.0]
  We are the first to apply the Fisher-Merging method to Sequential Recommendation, addressing and resolving practical challenges associated with it. We demonstrate the effectiveness of our proposed methods, highlighting their potential to advance the state-of-the-art in sequential learning and recommendation systems.
  arXiv  Detail & Related papers  (2023-07-05T05:58:56Z)
• Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning [68.45370492516531]
  We introduce Scalarized Multi-Objective Reinforcement Learning (SMORL) for the Recommender Systems (RS) setting. SMORL agent augments standard recommendation models with additional RL layers that enforce it to simultaneously satisfy three principal objectives: accuracy, diversity, and novelty of recommendations. Our experimental results on two real-world datasets reveal a substantial increase in aggregate diversity, a moderate increase in accuracy, reduced repetitiveness of recommendations, and demonstrate the importance of reinforcing diversity and novelty as complementary objectives.
  arXiv  Detail & Related papers  (2021-10-28T13:22:45Z)
• D2RLIR : an improved and diversified ranking function in interactive recommendation systems based on deep reinforcement learning [0.3058685580689604]
  This paper proposes a deep reinforcement learning based recommendation system by utilizing Actor-Critic architecture. The proposed model is able to generate a diverse while relevance recommendation list based on the user's preferences.
  arXiv  Detail & Related papers  (2021-10-28T13:11:29Z)
• Quadratic mutual information regularization in real-time deep CNN models [51.66271681532262]
  Regularization method motivated by the Quadratic Mutual Information is proposed. Experiments on various binary classification problems are performed, indicating the effectiveness of the proposed models.
  arXiv  Detail & Related papers  (2021-08-26T13:14:24Z)
• Learning User Representations with Hypercuboids for Recommender Systems [26.80987554753327]
  Our model explicitly models user interests as a hypercuboid instead of a point in the space. We present two variants of hypercuboids to enhance the capability in capturing the diversities of user interests. A neural architecture is also proposed to facilitate user hypercuboid learning by capturing the activity sequences (e.g., buy and rate) of users.
  arXiv  Detail & Related papers  (2020-11-11T12:50:00Z)

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.