28 citations · 96 across the 21 of their papers we have counts for
21 papers
Unified Demonstration Retriever for In-Context Learning
Xiaonan Li, Kai Lv, Hang Yan +6
In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction.…
Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation
Huanran Zheng, Wei Zhu, Pengfei Wang +1
Non-autoregressive translation (NAT) model achieves a much faster inference speed than the autoregressive translation (AT) model because it can simultaneously predict all tokens du…
Localized Adversarial Domain Generalization
Wei Zhu, Le Lu, Jing Xiao +3
Deep learning methods can struggle to handle domain shifts not seen in training data, which can cause them to not generalize well to unseen domains. This has led to research attent…
A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation
Tianxiang Sun, Xiangyang Liu, Wei Zhu +7
Early exiting allows instances to exit at different layers according to the estimation of difficulty. Previous works usually adopt heuristic metrics such as the entropy of internal…
Structure-preserving GANs
Jeremiah Birrell, Markos A. Katsoulakis, Luc Rey-Bellet +1
Generative adversarial networks (GANs), a class of distribution-learning methods based on a two-player game between a generator and a discriminator, can generally be formulated as…
Deformation Robust Roto-Scale-Translation Equivariant CNNs
Liyao Gao, Guang Lin, Wei Zhu
Incorporating group symmetry directly into the learning process has proved to be an effective guideline for model design. By producing features that are guaranteed to transform cov…
Neural Networks Enforcing Physical Symmetries in Nonlinear Dynamical Lattices: The Case Example of the Ablowitz-Ladik Model
Wei Zhu, Wesley Khademi, Efstathios G. Charalampidis +1
In this work we introduce symmetry-preserving, physics-informed neural networks (S-PINNs) motivated by symmetries that are ubiquitous to solutions of nonlinear dynamical lattices.…
Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis
Wei Zhu, Zihe Zheng, Haitian Zheng +2
Visual sentiment analysis has received increasing attention in recent years. However, the dataset's quality is a concern because the sentiment labels are crowd-sourcing, subjective…
Federated Learning of Molecular Properties with Graph Neural Networks in a Heterogeneous Setting
Wei Zhu, Jiebo Luo, Andrew White
Chemistry research has both high material and computational costs to conduct experiments. Institutions thus consider chemical data to be valuable and there have been few efforts to…
Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization
Wei Zhu, Haitian Zheng, Haofu Liao +2
Deep learning algorithms mine knowledge from the training data and thus would likely inherit the dataset's bias information. As a result, the obtained model would generalize poorly…
Lex-BERT: Enhancing BERT based NER with lexicons
Wei Zhu, Daniel Cheung
In this work, we represent Lex-BERT, which incorporates the lexicon information into Chinese BERT for named entity recognition (NER) tasks in a natural manner. Instead of using wor…
CMV-BERT: Contrastive multi-vocab pretraining of BERT
Wei Zhu, Daniel Cheung
In this work, we represent CMV-BERT, which improves the pretraining of a language model via two ingredients: (a) contrastive learning, which is well studied in the area of computer…
MVP-BERT: Redesigning Vocabularies for Chinese BERT and Multi-Vocab Pretraining
Wei Zhu
Despite the development of pre-trained language models (PLMs) significantly raise the performances of various Chinese natural language processing (NLP) tasks, the vocabulary for th…
Predicting Parkinson's Disease with Multimodal Irregularly Collected Longitudinal Smartphone Data
Weijian Li, Wei Zhu, E. Ray Dorsey +1
Parkinsons Disease is a neurological disorder and prevalent in elderly people. Traditional ways to diagnose the disease rely on in-person subjective clinical evaluations on the qua…
AutoRC: Improving BERT Based Relation Classification Models via Architecture Search
Wei Zhu, Xipeng Qiu, Yuan Ni +1
Although BERT based relation classification (RC) models have achieved significant improvements over the traditional deep learning models, it seems that no consensus can be reached…
AutoTrans: Automating Transformer Design via Reinforced Architecture Search
Wei Zhu, Xiaoling Wang, Xipeng Qiu +2
Though the transformer architectures have shown dominance in many natural language understanding tasks, there are still unsolved issues for the training of transformer models, espe…
Personalized Fashion Recommendation from Personal Social Media Data: An Item-to-Set Metric Learning Approach
Haitian Zheng, Kefei Wu, Jong-Hwi Park +2
With the growth of online shopping for fashion products, accurate fashion recommendation has become a critical problem. Meanwhile, social networks provide an open and new data sour…
Alleviating the Incompatibility between Cross Entropy Loss and Episode Training for Few-shot Skin Disease Classification
Wei Zhu, Haofu Liao, Wenbin Li +2
Skin disease classification from images is crucial to dermatological diagnosis. However, identifying skin lesions involves a variety of aspects in terms of size, color, shape, and…
Unifying Specialist Image Embedding into Universal Image Embedding
Yang Feng, Futang Peng, Xu Zhang +7
Deep image embedding provides a way to measure the semantic similarity of two images. It plays a central role in many applications such as image search, face verification, and zero…
Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters
Wei Zhu, Qiang Qiu, Robert Calderbank +2
Encoding the scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many computer vision tasks especially when deali…
Deep Neural Nets with Interpolating Function as Output Activation
Bao Wang, Xiyang Luo, Zhen Li +3
We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function. And we propose end-to-end training and testing algorithms for th…