no code implementations • 16 Apr 2024 • Jinhui Yuan, Shan Lu, Peibo Duan, Jieyue He
Recently, heterogeneous graph neural networks (HGNNs) have achieved impressive success in representation learning by capturing long-range dependencies and heterogeneity at the node level.
no code implementations • 29 Jan 2024 • Lingning Song, Yi Zu, Shan Lu, Jieyue He
Answering complex logical queries on incomplete knowledge graphs (KGs) is a fundamental and challenging task in multi-hop reasoning.
no code implementations • 29 Nov 2023 • Hua Pu, Jiacong Mi, Shan Lu, Jieyue He
Traditional Chinese medicine (TCM) prescription is the most critical form of TCM treatment, and uncovering the complex nonlinear relationship between symptoms and TCM is of great significance for clinical practice and assisting physicians in diagnosis and treatment.
no code implementations • 28 Nov 2023 • Zhuoyuan Wang, Jiacong Mi, Shan Lu, Jieyue He
An effective representation of drug molecules emerges as a pivotal component in this pursuit.
1 code implementation • 26 Oct 2023 • Shan Lu, Zhicheng Dong, Donghong Cai, Fang Fang, Dongcai Zhao
To avoid the local optimal solution of loss function and the model collapse, we introduce an exponential information measure into the loss function of GAN.
1 code implementation • 11 Oct 2023 • YuHan Liu, Hanchen Li, Yihua Cheng, Siddhant Ray, YuYang Huang, Qizheng Zhang, Kuntai Du, Jiayi Yao, Shan Lu, Ganesh Ananthanarayanan, Michael Maire, Henry Hoffmann, Ari Holtzman, Junchen Jiang
Compared to the recent systems that reuse the KV cache, CacheGen reduces the KV cache size by 3. 7-4. 3x and the total delay in fetching and processing contexts by 2. 7-3. 2x while having negligible impact on the LLM response quality in accuracy or perplexity.
no code implementations • 7 Oct 2023 • YuHan Liu, Chengcheng Wan, Kuntai Du, Henry Hoffmann, Junchen Jiang, Shan Lu, Michael Maire
ML APIs have greatly relieved application developers of the burden to design and train their own neural network models -- classifying objects in an image can now be as simple as one line of Python code to call an API.
1 code implementation • 20 Apr 2023 • Mingjun Zhao, Shan Lu, Zixuan Wang, Xiaoli Wang, Di Niu
Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training.
no code implementations • 29 Sep 2021 • Yu Song, Shan Lu, Dehong Qiu
The key idea is node classification can benefit from various variants of the original graph that are more efficient for message propagation, based upon the assumption that each variant is a potential structure as more nodes are properly labeled.
no code implementations • ICML 2020 • Chengcheng Wan, Henry Hoffmann, Shan Lu, Michael Maire
We propose a novel variant of SGD customized for training network architectures that support anytime behavior: such networks produce a series of increasingly accurate outputs over time.
no code implementations • 31 Oct 2019 • Chengcheng Wan, Muhammad Santriaji, Eri Rogers, Henry Hoffmann, Michael Maire, Shan Lu
An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans.