287 citations
- University of Science and Technology of ChinaCN10 papers
- Chinese Academy of SciencesCN8 papers
- Institute of Computing TechnologyCN8 papers
- Stanford UniversityUS8 papers
- Zhejiang UniversityCN8 papers
- Alibaba Group (China)CN7 papers
- Microsoft Research (United Kingdom)GB7 papers
- Peking UniversityCN7 papers
- University of Hong KongHK7 papers
- Carnegie Mellon UniversityUS6 papers
- Google (United States)US6 papers
- Jingdong (China)CN6 papers
51 papers · 1 filter
GIPA: A General Information Propagation Algorithm for Graph Learning
Houyi Li, Zhihong Chen, Zhao Li +3
Graph neural networks (GNNs) have been widely used in graph-structured data computation, showing promising performance in various applications such as node classification, link pre…
Sayer: Using Implicit Feedback to Optimize System Policies
Mathias Lécuyer, Sang Hoon Kim, Mihir Nanavati +4
We observe that many system policies that make threshold decisions involving a resource (e.g., time, memory, cores) naturally reveal additional, or implicit feedback. For example,…
Stable Prediction on Graphs with Agnostic Distribution Shift
Shengyu Zhang, Kun Kuang, Jiezhong Qiu +5
Graph is a flexible and effective tool to represent complex structures in practice and graph neural networks (GNNs) have been shown to be effective on various graph tasks with rand…
Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
Bencheng Yan, Pengjie Wang, Kai Zhang +4
Embedding learning for categorical features is crucial for the deep learning-based recommendation models (DLRMs). Each feature value is mapped to an embedding vector via an embeddi…
AdaRNN: Adaptive Learning and Forecasting of Time Series
Yuntao Du, Jindong Wang, Wenjie Feng +4
Time series has wide applications in the real world and is known to be difficult to forecast. Since its statistical properties change over time, its distribution also changes tempo…
Relational Graph Neural Networks for Fraud Detection in a Super-App environment
Jaime D. Acevedo-Viloria, Luisa Roa, Soji Adeshina +4
Large digital platforms create environments where different types of user interactions are captured, these relationships offer a novel source of information for fraud detection pro…