OneRank：一种统一的Transformer与原生排序架构，适用于多任务推荐场景
OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation
摘要
多任务学习在推荐系统中起着至关重要的作用，它能够实现不同用户反馈之间的互补学习。虽然现代工业实践已经从依赖深度神经网络的结构转向以Transformer为核心的架构，以提升序列建模能力和扩展性，但这些架构仍然将特征编码与多任务预测分离开来，使得Transformer只能作为与任务无关的编码器来发挥作用。这种设计从根本上限制了系统的性能和可扩展性：首先，异构任务目标导致信息传递出现瓶颈；其次，梯度干扰会导致系统出现“跷跷板效应”；最后，系统需要经历一种数据流转换过程，即基于上下文的表示学习被转换为静态的前向传播任务预测，而这种转换方式并不兼容。 我们提出了OneRank这一基于Transformer的多任务排序框架。该框架消除了编码器与预测器之间的分离，同时引入了针对特定任务的通道，用于前向表示学习和后向优化，从而实现针对特定任务的学习，同时减少不同任务之间的干扰。在前向传播过程中，OneRank通过基于任务条件的信息选择、考虑候选节点的上下文处理以及控制性的跨任务交互，自下而上地构建出与任务相关的表示。在后向传播过程中，跨任务的梯度分离使得任务特定的参数更新与共享知识提取模块分离，从而避免了负面影响的产生。此外，我们还用基于动态匹配的评分机制取代了传统的静态任务特定MLP评分器，从而实现基于上下文的个性化排序。通过将多任务推理整合到Transformer框架中，OneRank建立了一个统一且可扩展的架构模式。在大规模工业数据集上的离线及在线实验中表明，OneRank在保持计算效率的同时，其性能明显优于现有的最佳基线算法。
English Abstract
Multi-task learning (MTL) is essential in recommender systems to enable complementary learning among diverse user feedback. While modern industrial practices have shifted from DNNs to Transformer-centric architectures to strengthen sequence modeling and scaling capacity, they still decouple feature encoding from multi-task prediction, treating the Transformer as a task-agnostic encoder. This design fundamentally limits the performance and scalability by (1) creating an information bottleneck under heterogeneous task objectives, (2) inducing gradient interference that leads to the seesaw phenomenon, and (3) forcing a dataflow transition in which attention-based, context-adaptive representation learning is converted to static feed-forward task prediction with incompatible information read-write dynamics. We propose OneRank, a Transformer-native multi-task ranking framework that eliminates encoder-predictor separation and introduces task-private channels for forward representation learning and backward optimization, enabling task-specialized learning while reducing inter-task interference. In the forward pass, OneRank learns task-specific representations bottom-up through task-conditioned information selection, candidate-aware contextualization, and controlled cross-task interaction. In the backward pass, cross-task gradient detachment isolates task-private parameter updates from shared knowledge extraction modules, preventing negative transfer. We further replace static task-specific MLP scorers with dynamic matching-based scoring for context-aware personalized ranking. By internalizing multi-task reasoning within the Transformer stack, OneRank establishes a unified and scalable architectural paradigm. Offline and online experiments on large-scale industrial datasets show that OneRank significantly outperforms state-of-the-art baselines while maintaining computational efficiency.