Recent emergence of multilingual pre-training language model (mPLM) has enabled breakthroughs on various downstream cross-lingual transfer (CLT) tasks.
Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i. e., class centers) in a hyper-sphere manifold.
Transferability estimation has been an essential tool in selecting a pre-trained model and the layers of it to transfer, so as to maximize the performance on a target task and prevent negative transfer.
How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world.
Specifically, AST adopts a Sparse Transformer as the generator to learn a sparse attention map for time series forecasting, and uses a discriminator to improve the prediction performance from sequence level.
Moreover, both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets and are compatible with existing meta-learning algorithms.
Deep learning based medical image diagnosis has shown great potential in clinical medicine.
no code implementations • 4 Jul 2020 • Yue Sun, Kun Gao, Zhengwang Wu, Zhihao Lei, Ying WEI, Jun Ma, Xiaoping Yang, Xue Feng, Li Zhao, Trung Le Phan, Jitae Shin, Tao Zhong, Yu Zhang, Lequan Yu, Caizi Li, Ramesh Basnet, M. Omair Ahmad, M. N. S. Swamy, Wenao Ma, Qi Dou, Toan Duc Bui, Camilo Bermudez Noguera, Bennett Landman, Ian H. Gotlib, Kathryn L. Humphreys, Sarah Shultz, Longchuan Li, Sijie Niu, Weili Lin, Valerie Jewells, Gang Li, Dinggang Shen, Li Wang
Deep learning-based methods have achieved state-of-the-art performance; however, one of major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners.
We pre-train GROVER with 100 million parameters on 10 million unlabelled molecules -- the biggest GNN and the largest training dataset in molecular representation learning.
no code implementations • 7 May 2020 • Liang Sun, Zhanhao Mo, Fuhua Yan, Liming Xia, Fei Shan, Zhongxiang Ding, Wei Shao, Feng Shi, Huan Yuan, Huiting Jiang, Dijia Wu, Ying WEI, Yaozong Gao, Wanchun Gao, He Sui, Daoqiang Zhang, Dinggang Shen
We evaluated our proposed AFS-DF on COVID-19 dataset with 1495 patients of COVID-19 and 1027 patients of community acquired pneumonia (CAP).
no code implementations • 7 May 2020 • Donglin Di, Feng Shi, Fuhua Yan, Liming Xia, Zhanhao Mo, Zhongxiang Ding, Fei Shan, Shengrui Li, Ying WEI, Ying Shao, Miaofei Han, Yaozong Gao, He Sui, Yue Gao, Dinggang Shen
The main challenge in early screening is how to model the confusing cases in the COVID-19 and CAP groups, with very similar clinical manifestations and imaging features.
no code implementations • 6 May 2020 • Xi Ouyang, Jiayu Huo, Liming Xia, Fei Shan, Jun Liu, Zhanhao Mo, Fuhua Yan, Zhongxiang Ding, Qi Yang, Bin Song, Feng Shi, Huan Yuan, Ying WEI, Xiaohuan Cao, Yaozong Gao, Dijia Wu, Qian Wang, Dinggang Shen
To this end, we develop a dual-sampling attention network to automatically diagnose COVID- 19 from the community acquired pneumonia (CAP) in chest computed tomography (CT).
There are two main challenges: 1) the discrepancy of data distributions between domains; 2) the task difference between the diagnosis of typical pneumonia and COVID-19.
The worldwide spread of coronavirus disease (COVID-19) has become a threatening risk for global public health.
Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance.
In this paper, we propose a dual aggregation network to adaptively aggregate different information in infant brain MRI segmentation.
In this paper, we seek to exploit rich labeled data from relevant domains to help the learning in the target task with unsupervised domain adaptation (UDA).
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem.
Towards the challenging problem of semi-supervised node classification, there have been extensive studies.
Automated machine learning aims to automate the whole process of machine learning, including model configuration.
In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks.
Specifically, our proposed model is designed as a spatial-temporal network with a meta-learning paradigm.
Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT).
In transfer learning, what and how to transfer are two primary issues to be addressed, as different transfer learning algorithms applied between a source and a target domain result in different knowledge transferred and thereby the performance improvement in the target domain.
Based on such training set, L2MT first uses a proposed layerwise graph neural network to learn task embeddings for all the tasks in a multitask problem and then learns an estimation function to estimate the relative test error based on task embeddings and the representation of the multitask model based on a unified formulation.
Existing cross-domain sentiment classification meth- ods cannot automatically capture non-pivots, i. e., the domain- specific sentiment words, and pivots, i. e., the domain-shared sentiment words, simultaneously.
We establish the L2T framework in two stages: 1) we first learn a reflection function encrypting transfer learning skills from experiences; and 2) we infer what and how to transfer for a newly arrived pair of domains by optimizing the reflection function.