arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.17428cs.LG
收藏

选择合适的权重:在推荐系统中平衡价值、策略与噪声

Choosing the Right Weights: Balancing Value, Strategy, and Noise in Recommender Systems

Cornell Tech(康奈尔科技学院)

Smitha Milli, Emma Pierson, Nikhil Garg

AI总结:

该研究从用户与内容生产者双视角分析推荐系统行为权重的最优选择,提出基于价值忠实度、策略鲁棒性、噪声的分析框架,经Facebook大规模数据集验证,用户最优权重既提升用户价值,还意外改善了信息质量等社会结果。

摘要:

许多推荐系统会对不同用户行为(如点击、点赞和分享)进行线性加权并优化该加权值。我们从用户以及会对权重做出策略性响应的内容生产者双重视角,分析了权重的最优选择问题。我们考虑了每种潜在行为的三个维度:价值忠实度(一种行为能在多大程度上表明用户是否重视该内容)、策略鲁棒性(生产者操纵该行为的难度),以及噪声程度(预测该行为时的估计误差大小)。我们的理论结果表明,对用户而言,提高更具价值忠实度、噪声更低的行为的权重,能带来更高的效用;而对生产者而言,提高更具价值忠实度和策略鲁棒性的行为的权重,能带来更高的福利(且噪声的影响是非单调的)。最后,我们将该框架应用于Facebook的权重设计,使用了约7000万个在Facebook上分享的URL构成的大规模数据集。值得注意的是,我们发现用户最优权重向量(a)比未考虑方差的权重向量能带来更高的用户价值;(b)还能改善更广泛的社会结果,减少错误信息并提升URL域名的质量,而这些结果并未在我们的理论框架中被直接设定为目标。

英文摘要:

Many recommender systems optimize a linear weighting of different user behaviors, such as clicks, likes, and shares. We analyze the optimal choice of weights from the perspectives of both users and content producers who strategically respond to the weights. We consider three aspects of each potential behavior: value-faithfulness (how well a behavior indicates whether the user values the content), strategy-robustness (how hard it is for producers to manipulate the behavior), and noisiness (how much estimation error there is in predicting the behavior). Our theoretical results show that for users, up-weighting more value-faithful and less noisy behaviors leads to higher utility, while for producers, up-weighting more value-faithful and strategy-robust behaviors leads to higher welfare (and the impact of noise is non-monotonic). Finally, we apply our framework to design weights on Facebook, using a large-scale dataset of approximately 70 million URLs shared on Facebook. Strikingly, we find that our user-optimal weight vector (a) delivers higher user value than a vector not accounting for variance; (b) also enhances broader societal outcomes, reducing misinformation and raising the quality of the URL domains, outcomes that were not directly targeted in our theoretical framework.

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。

↑