让搜索结果更公平,避免小众意图被忽略。
Diversification as Risk Minimization
- 把多样性排序看作风险最小化问题,关注最不受照顾的用户意图。
- 新方法VRisker能将最差意图失败率降低33%,平均效果仅降2%。
- 适合关心搜索公平性、用户体验的算法研究者和工程师。
用户往往更记得搜索会话中的失败,而非众多成功。现有研究关注整体鲁棒性,但忽略了单个查询内不同用户意图的平衡问题。例如‘jaguar’这类模糊查询可能对应多种意图,主流意图常主导排名,导致少数意图用户不满。尽管多样性研究长期关注此问题,现有指标仅衡量平均相关性,缺乏鲁棒性保障。我们理论与实证表明,许多知名多样性算法的鲁棒性甚至不如非多样性基线。为此,我们提出将多样性建模为风险最小化问题,引入VRisk度量最少服务意图所面临的风险。优化VRisk可生成更具鲁棒性的排序。进一步提出快速贪心重排算法VRisker,具有可证明的近似保证。在NTCIR INTENT-2、TREC Web 2012和MovieLens上的实验显示,现有方法存在明显脆弱性。VRisker最多减少33%的最差意图失败率,平均性能仅下降2%。
原文摘要 · Abstract (English)
Users tend to remember failures of a search session more than its many successes. This observation has led to work on search robustness, where systems are penalized if they perform very poorly on some queries. However, this principle of robustness has been overlooked within a single query. An ambiguous or underspecified query (e.g., ``jaguar'') can have several user intents, where popular intents often dominate the ranking, leaving users with minority intents unsatisfied. Although the diversification literature has long recognized this issue, existing metrics only model the average relevance across intents and provide no robustness guarantees. More surprisingly, we show theoretically and empirically that many well-known diversification algorithms are no more robust than a naive, non-diversified algorithm. To address this critical gap, we propose to frame diversification as a risk-minimization problem. We introduce VRisk, which measures the expected risk faced by the least-served fraction of intents in a query. Optimizing VRisk produces a robust ranking, reducing the likelihood of poor user experiences. We then propose VRisker, a fast greedy re-ranker with provable approximation guarantees. Finally, experiments on NTCIR INTENT-2, TREC Web 2012, and MovieLens show the vulnerability of existing methods. VRisker reduces worst-case intent failures by up to 33% with a minimal 2% drop in average performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。