Although advancements in deep learning have significantly enhanced the recommendation accuracy of deep recommendation models, these methods still suffer from low recommendation efficiency. Recently proposed tree-based deep recommendation models alleviate the problem by directly learning tree structure and representations under the guidance of recommendation objectives. To guarantee the effectiveness of beam search for recommendation accuracy, these models strive to ensure that the tree adheres to the max-heap assumption, where a parent node's preference should be the maximum among its children's preferences. However, they employ a one-versus-all strategy, framing the training task as a series of independent binary classification objectives for each node, which limits their ability to fully satisfy the max-heap assumption. To this end, we propose a Deep Tree-based Retriever (DTR for short) for efficient recommendation. DTR frames the training task as a softmax-based multi-class classification over tree nodes at the same level, enabling explicit horizontal competition and more discriminative top-k selection among them, which mimics the beam search behavior during training. To mitigate the suboptimality induced by the labeling of non-leaf nodes, we propose a rectification method for the loss function, which further aligns with the max-heap assumption in expectation. As the number of tree nodes grows exponentially with the levels, we employ sampled softmax to approximate optimization and thereby enhance efficiency. Furthermore, we propose a tree-based sampling method to reduce the bias inherent in sampled softmax. Theoretical results reveal DTR's generalization capability, and both the rectification method and tree-based sampling contribute to improved generalization. The experiments are conducted on four real-world datasets, validating the effectiveness of the proposed method.
Cooperative Retriever and Ranker in Deep Recommenders
University of Science and Technology of China（中国科学技术大学）；University of Electronic Science and Technology of China（电子科技大学）；Microsoft Research Asia（微软亚洲研究院）
Pairwise and Attribute-Aware Decision Tree-Based Preference Elicitation for Cold-Start Recommendation
KU Leuven, Campus Kulak, Department of Public Health and Primary Care（KU莱顿大学）；Itec, imec research group at KU Leuven（Itec）；KU Leuven, Department of Mathematics（KU莱顿大学）
Joint Optimization of Tree-based Index and Deep Model for Recommender Systems
Alibaba Group（阿里巴巴集团）；Tsinghua University（清华大学）
大型工业推荐系统通常面临着巨大的语料库规模的计算问题。为了在响应时间限制下检索并向用户推荐最相关的项目，采用高效的索引结构是一种有效且实用的解决方案。基于树的深度模型（Tree-based Deep Model，TDM）\cite{zhu2018learning}使用树索引极大地提高了推荐的准确性。通过索引树层次结构中的项并训练满足树中的类最大堆性质的用户节点偏好预测模型，TDM提供了相对于树的对数计算复杂性。语料库的大小，使得在候选检索和推荐中能够使用任意的高级模型。在基于树的推荐方法中，树索引和用户节点偏好预测模型的质量在很大程度上决定了推荐的准确性。我们认为树索引和偏好模型的学习具有相互依赖性。我们的目的，在本文中，是开发一种方法来共同学习的索引结构和用户偏好预测模型。在我们提出的联合优化框架中，索引的学习和用户偏好预测模型在统一的性能指标下进行。此外，我们提出了一种新的层次用户偏好表示利用树索引层次。两个大规模真实数据集的实验结果表明，该方法显著提高了推荐准确率。在线A/B测试结果显示广告平台也证明了该方法在生产环境中的有效性。
Hypergraph Enhanced Knowledge Tree Prompt Learning for Next-Basket Recommendation
Sun Yat-Sen University（中山大学）；Wens Foodstuff Group Co., Ltd.（温氏食品集团股份有限公司）；Guangdong Polytechnic Normal University（广东技术师范大学）；University of Illinois（伊利诺伊大学）
Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search
College of Computer Science, Sichuan University（四川大学计算机学院）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究院）；School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算与信息系统学院）
