WeGR:微信工业搜索系统的统一生成式检索
WeGR: Towards Unified Generative Retrieval via Behavior-aware Tokenization and Preference Alignment
AI总结:
针对工业搜索生成式检索的两大挑战,提出WeGR框架,含CoCo-VAE与DHPO组件,经离线实验及微信电商搜索在线测试,性能提升且资源消耗降低,已部署于微信多搜索场景。
摘要:
生成式检索(GR)通过在自回归框架内统一候选生成,为工业搜索提供了极具前景的范式,但其有效性受限于两大关键挑战。其一,现有语义ID(SID)分词器难以在维持有效码本利用率的同时融入协作信号,限制了其区分物品和实现高质量检索的能力。其二,现有强化学习(RL)方法在精确SID匹配下存在严重的奖励稀疏问题,导致大量采样轨迹缺乏有效学习信号,阻碍了偏好优化。为应对这些挑战,我们提出WeGR,一个由两个互补组件构成的统一生成式检索框架。具体而言,协作无崩溃分词器(CoCo-VAE)融入查询到物品及物品到物品的协作信号,同时通过码本刷新和互补正则化缓解码本崩溃,从而实现更具信息量和平衡性的SID表示。基于这些SID,动态视界策略优化(DHPO)逐步扩展奖励评估和策略优化视界,降低学习难度,同时利用SID层级不同层面的行为奖励信号,无需依赖辅助奖励模型。大量离线实验证明了WeGR在提升检索和排序性能方面的有效性。此外,在微信电商搜索开展的为期两个月的在线A/B测试显示,其订单量相对提升2.539%,点击率相对提升1.508%,转化率相对提升1.381%,同时在线CPU和GPU使用量分别降低25.5%和26.1%。该系统已成功部署于微信多个搜索场景,服务数十亿用户,每日产生数千万页面浏览量(PV)。
英文摘要:
Generative retrieval (GR) offers a promising paradigm for industrial search by unifying candidate generation within an autoregressive framework. However, effectively leveraging user behaviors in industrial GR remains challenging: existing SID tokenization methods struggle to preserve collaborative signals while maintaining balanced codebook utilization, whereas reinforcement learning (RL) for prioritizing high-value candidates suffers from sparse rewards when generated SIDs fail to match positive items. To address these challenges, we propose WeGR, a unified GR framework with two complementary components. Specifically, the Collaborative and Collapse-free Tokenizer (CoCo-VAE) injects query-to-item and item-to-item collaborative signals into continuous representations before quantization, preserving behavioral information without disrupting codebook optimization. It further couples first-layer codebook refresh to reactivate underutilized codewords with fidelity anti-collapse regularization, which broadens gradient coverage over relevant codewords and penalizes collisions in deeper layers to yield behavior-aware SIDs with balanced utilization. For preference alignment, Dynamic Horizon Policy Optimization (DHPO) progressively expands reward evaluation and policy optimization horizons to alleviate reward sparsity, enabling coarse-to-fine preference learning from SID prefixes to complete items without auxiliary reward models. Extensive offline experiments validate that WeGR improves retrieval and ranking performance. Moreover, a six-week online A/B test on a large-scale e-commerce search platform achieves relative gains of 2.539% in orders, 1.508% in CTR, and 1.381% in CVR, while reducing CPU and GPU usage by 25.5% and 26.1%. These results highlight the effectiveness and efficiency of WeGR in industrial deployment, supporting multiple search scenarios and tens of millions of daily page views.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。