1 code implementation • ICLR 2022 • Shuming Kong, Yanyan Shen, Linpeng Huang
To achieve this, we use influence functions to estimate how relabeling a training sample would affect model's test performance and further develop a novel relabeling function R. We theoretically prove that applying R to relabel harmful training samples allows the model to achieve lower test loss than simply discarding them for any classification tasks using cross-entropy loss.
no code implementations • 8 Jun 2020 • Weiyu Cheng, Yanyan Shen, Linpeng Huang
The dimensions of different feature embeddings are often set to a same value empirically, which limits the predictive performance of latent factor models.
4 code implementations • 7 Sep 2019 • Weiyu Cheng, Yanyan Shen, Linpeng Huang
Various factorization-based methods have been proposed to leverage second-order, or higher-order cross features for boosting the performance of predictive models.
Ranked #3 on Click-Through Rate Prediction on MovieLens
1 code implementation • KDD 2019 2019 • Weiyu Cheng, Yanyan Shen, Linpeng Huang, Yanmin Zhu
The results demonstrate the effectiveness and efficiency of FIA, and the usefulness of the generated explanations for the recommendation results.
no code implementations • 3 Jun 2019 • Xian Zhou, Yanyan Shen, Linpeng Huang
However, existing traffic prediction methods focus on modeling complex spatiotemporal traffic correlations and seldomly study the influence of the original traffic flows among regions.
no code implementations • 20 Nov 2018 • Weiyu Cheng, Yanyan Shen, Yanmin Zhu, Linpeng Huang
Latent factor models (LFMs) such as matrix factorization achieve the state-of-the-art performance among various Collaborative Filtering (CF) approaches for recommendation.
1 code implementation • AAAI 2018 • Weiyu Cheng, Yanyan Shen, Yanmin Zhu, Linpeng Huang
We leverage both the information from monitoring stations and urban data that are closely related to air quality, including POIs, road networks and meteorology.