TiTle：Taming Latent Factor Models for Explainability
题目：驯服隐变量模型以实现推荐系统中的可解释性
Abstract:
Latent factor and neural network models have achieved great success in personalized recommendations, but they are also notoriously difficult to explain. In this talk, I will share our recent effort in integrating regression trees and generative models to guide the learning of latent factor models for explainable recommendation. Specifically, we build regression trees on users and items recursively based on user-provided review content, and associate a latent factor to each node on the trees to represent users and items for recommendation. With the growth of regression tree, we are able to track the creation of latent factors by looking into the path of each factor on regression trees, which thus serves as an explanation for the resulting recommendations. If time allows, I would also like to share our progress in multi-task tensor factorization and generative neural collaborative filtering for explainable recommendation.
摘要：
隐变量模型在个性化推荐系统中已取得极大的成功，但它在推荐过程与结果上的不可解释性也往往受到严重的诟病。在本次讲座中，我将分享我们最近在利用回归树指导隐变量模型学习以实现可解释推荐方向所做的尝试。在算法上我们根据用户提供的评论信息内容递归地构建用户与推荐对象的回归树，并将隐变量直接关联到树上的每个节点来表示用户和推荐对象从而完成自动推荐。根据回归树的构建过程，我们能够通过查看回归树上每个隐变量的创建路径来对其产生的推荐进行解释。如果时间允许，我还将分享我们近期在基于多任务张量分解和生成式神经网络协同过滤模型的可解释性上的研究进展。
Bio:
Dr. Hongning Wang is now an Associate Professor in the Department of Computer Science at the University of Virginia. He received his PhD degree in computer science at the University of Illinois at Champaign-Urbana in 2014. His research generally lies in the intersection among machine learning, data mining and information retrieval, with a special focus on sequential decision optimization and computational user modeling. His work has generated over 80 research papers in top venues in data mining and information retrieval areas. He is a recipient of 2016 National Science Foundation CAREER Award, 2020 Google Faculty Research Award, and SIGIR’2019 Best Paper Award.
王宏宁博士现任美国弗吉尼亚大学计算机系副教授。他于2014博士毕业于美国伊利诺伊大学香槟分校，研究方向主要集中于机器学习、数据挖掘和信息检索，尤其着眼于面向用户的交互式建模与决策优化。他的研究小组在此方向已发表80余篇论文，并获得SIGIR2019最佳论文奖、美国自然科学基金2016青年学者奖和Google 2020教师研究奖。
报告时间：2021年12月20日（星期一）上午9:00
报告地点：正新楼（原水务集团大楼）三楼报告厅
主办单位：人工智能学院
