Hierarchical Group-wise Ranking Framework for Recommendation Models

In modern recommender systems, CTR/CVR models are increasingly trained with ranking objectives to improve item ranking quality. While this shift aligns training more closely with serving goals, most existing methods rely on in-batch negative sampling, which predominantly surfaces easy negatives. This limits the model's ability to capture fine-grained user preferences and weakens overall ranking performance. To address this, we propose a Hierarchical Group-wise Ranking Framework with two key components. First, we apply residual vector quantization to user embeddings to generate hierarchical user codes that partition users into hierarchical, trie-structured clusters. Second, we apply listwise ranking losses to user-item pairs at each level of the hierarchy, where shallow levels group loosely similar users and deeper levels group highly similar users, reinforcing learning-to-rank signals through progressively harder negatives. Since users with similar preferences and content exposure tend to yield more informative negatives, applying ranking losses within these hierarchical user groups serves as an effective approximation of hard negative mining. Our approach improves ranking performance without requiring complex real-time context collection or retrieval infrastructure. Extensive experiments demonstrate that the proposed framework consistently enhances both model calibration and ranking accuracy, offering a scalable and practical solution for industrial recommender systems.

RankTower: A Synergistic Framework for Enhancing Two-Tower Pre-Ranking Model

In large-scale ranking systems, cascading architectures have been widely adopted to achieve a balance between efficiency and effectiveness. The pre-ranking module plays a vital role in selecting a subset of candidates for the subsequent ranking module. It is crucial for the pre-ranking model to maintain a balance between efficiency and accuracy to adhere to online latency constraints. In this paper, we propose a novel neural network architecture called RankTower, which is designed to efficiently capture user-item interactions while following the user-item decoupling paradigm to ensure online inference efficiency. The proposed approach employs a hybrid training objective that learns from samples obtained from the full stage of the cascade ranking system, optimizing different objectives for varying sample spaces. This strategy aims to enhance the pre-ranking model's ranking capability and improvement alignment with the existing cascade ranking system. Experimental results conducted on public datasets demonstrate that RankTower significantly outperforms state-of-the-art pre-ranking models.

AdaEnsemble: Learning Adaptively Sparse Structured Ensemble Network for Click-Through Rate Prediction

Learning feature interactions is crucial to success for large-scale CTR prediction in recommender systems and Ads ranking. Researchers and practitioners extensively proposed various neural network architectures for searching and modeling feature interactions. However, we observe that different datasets favor different neural network architectures and feature interaction types, suggesting that different feature interaction learning methods may have their own unique advantages. Inspired by this observation, we propose AdaEnsemble: a Sparsely-Gated Mixture-of-Experts (SparseMoE) architecture that can leverage the strengths of heterogeneous feature interaction experts and adaptively learns the routing to a sparse combination of experts for each example, allowing us to build a dynamic hierarchy of the feature interactions of different types and orders. To further improve the prediction accuracy and inference efficiency, we incorporate the dynamic early exiting mechanism for feature interaction depth selection. The AdaEnsemble can adaptively choose the feature interaction depth and find the corresponding SparseMoE stacking layer to exit and compute prediction from. Therefore, our proposed architecture inherits the advantages of the exponential combinations of sparsely gated experts within SparseMoE layers and further dynamically selects the optimal feature interaction depth without executing deeper layers. We implement the proposed AdaEnsemble and evaluate its performance on real-world datasets. Extensive experiment results demonstrate the efficiency and effectiveness of AdaEnsemble over state-of-the-art models.

xDeepInt: a hybrid architecture for modeling the vector-wise and bit-wise feature interactions

Learning feature interactions is the key to success for the large-scale CTR prediction and recommendation. In practice, handcrafted feature engineering usually requires exhaustive searching. In order to reduce the high cost of human efforts in feature engineering, researchers propose several deep neural networks (DNN)-based approaches to learn the feature interactions in an end-to-end fashion. However, existing methods either do not learn both vector-wise interactions and bit-wise interactions simultaneously, or fail to combine them in a controllable manner. In this paper, we propose a new model, xDeepInt, based on a novel network architecture called polynomial interaction network (PIN) which learns higher-order vector-wise interactions recursively. By integrating subspace-crossing mechanism, we enable xDeepInt to balance the mixture of vector-wise and bit-wise feature interactions at a bounded order. Based on the network architecture, we customize a combined optimization strategy to conduct feature selection and interaction selection. We implement the proposed model and evaluate the model performance on three real-world datasets. Our experiment results demonstrate the efficacy and effectiveness of xDeepInt over state-of-the-art models. We open-source the TensorFlow implementation of xDeepInt: https://github.com/yanyachen/xDeepInt.

DynInt: Dynamic Interaction Modeling for Large-scale Click-Through Rate Prediction

Learning feature interactions is the key to success for the large-scale CTR prediction in Ads ranking and recommender systems. In industry, deep neural network-based models are widely adopted for modeling such problems. Researchers proposed various neural network architectures for searching and modeling the feature interactions in an end-to-end fashion. However, most methods only learn static feature interactions and have not fully leveraged deep CTR models' representation capacity. In this paper, we propose a new model: DynInt. By extending Polynomial-Interaction-Network (PIN), which learns higher-order interactions recursively to be dynamic and data-dependent, DynInt further derived two modes for modeling dynamic higher-order interactions: dynamic activation and dynamic parameter. In dynamic activation mode, we adaptively adjust the strength of learned interactions by instance-aware activation gating networks. In dynamic parameter mode, we re-parameterize the parameters by different formulations and dynamically generate the parameters by instance-aware parameter generation networks. Through instance-aware gating mechanism and dynamic parameter generation, we enable the PIN to model dynamic interaction for potential industry applications. We implement the proposed model and evaluate the model performance on real-world datasets. Extensive experiment results demonstrate the efficiency and effectiveness of DynInt over state-of-the-art models.