近日，信息检索国际顶级会议（SIGIR 2021）公布了录用论文列表，实验室硕士生谢张的研究成果被录用为短文，将在会议上做口头报告。ACM SIGIR 是国际计算机协会信息检索大会的缩写，被CCF列为A级国际会议。SIGIR 专注于信息存储、检索和传播的各个方面，从1971年开始，每年召开一届。吸引了世界各地的信息检索领域研究者的持续关注，实验室长期致力于信息检索领域研究，期待这次与国内外同行的交流。录用论文题目和摘要如下：

题目：Info-flow Enhanced GANs for Recommender

摘要：Recommendation systems can help users process large amounts of information, and generative adversarial networks (GANs) show great potential in recommendation systems. Therefore, we propose a new GAN model in which the main idea is to enhance the information flow within the generator based on the information flow between the original generator and discriminator. Our experimental results indicate that our model reduces the discrepancy between the generator and the discriminator and that both the generator and discriminator have better performance and show considerable improvements compared to other strong baselines. The improvements of the NDCG@3 and MRR are significant, which can reach 30.98% and 30.17%, respectively.

中文简介：本文针对信息检索推荐任务，提出了一种对抗网络模型，该模型基于增强生成器信息流的方法，改善推荐模型性能，在实验数据集上的NDCG@3 和 MRR两项指标的结果提升显著。