most citedA novel meta-learning initialization method for physics-informed neural networks

81 citations · 130 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CL2021★ 4 cited

Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona

Weixuan Wang, Xiaoling Cai, Chong Hsuan Huang +4

In this paper, we describe approaches for developing Emily, an emotion-affective open-domain chatbot. Emily can perceive a user's negative emotion state and offer supports by posit…

cs.CV2021★ 2 cited

Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer

Haoyu Chen, Hao Tang, Henglin Shi +3

With the strength of deep generative models, 3D pose transfer regains intensive research interests in recent years. Existing methods mainly rely on a variety of constraints to achi…

cs.IR2021

TPRM: A Topic-based Personalized Ranking Model for Web Search

Minghui Huang, Wei Peng, Dong Wang

Ranking models have achieved promising results, but it remains challenging to design personalized ranking systems to leverage user profiles and semantic representations between que…

cs.LG2021★ 81 cited

A novel meta-learning initialization method for physics-informed neural networks

Xu Liu, Xiaoya Zhang, Wei Peng +2

Physics-informed neural networks (PINNs) have been widely used to solve various scientific computing problems. However, large training costs limit PINNs for some real-time applicat…

cs.LG2020★ 27 cited

Accelerating Physics-Informed Neural Network Training with Prior Dictionaries

Wei Peng, Weien Zhou, Jun Zhang +1

Physics-Informed Neural Networks (PINNs) can be regarded as general-purpose PDE solvers, but it might be slow to train PINNs on particular problems, and there is no theoretical gua…

cs.CL2020★ 14 cited

Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation

Wei Peng, Chongxuan Huang, Tianhao Li +2

Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora. These methods suffer f…