Share This Author
Representation Learning for Treatment Effect Estimation from Observational Data
A local similarity preserved individual treatment effect (SITE) estimation method based on deep representation learning that preserves local similarity and balances data distributions simultaneously, by focusing on several hard samples in each mini-batch.
A Survey on Causal Inference
- Liuyi Yao, Zhixuan Chu, Sheng Li, Yaliang Li, Jing Gao, Aidong Zhang
- Computer ScienceACM Trans. Knowl. Discov. Data
- 5 February 2020
This survey provides a comprehensive review of causal inference methods under the potential outcome framework, one of the well-known causal inference frameworks, and presents the plausible applications of these methods, including the applications in advertising, recommendation, medicine, and so on.
A Multi-View Deep Learning Framework for EEG Seizure Detection
- Ye Yuan, Guangxu Xun, Ke-bin Jia, Aidong Zhang
- Computer ScienceIEEE Journal of Biomedical and Health Informatics
A new autoencoder-based multi-view learning model is constructed by incorporating both inter and intra correlations of EEG channels to unleash the power of multi-channel information by adding a channel-wise competition mechanism in the training phase.
Deep Patient Similarity Learning for Personalized Healthcare
- Qiuling Suo, Fenglong Ma, Aidong Zhang
- Computer ScienceIEEE Transactions on NanoBioscience
- 16 May 2018
This paper uses a convolutional neural network to capture local important information in EHRs and then feeds the learned representation into triplet loss or softmax cross entropy loss, which can better represent the longitudinal EHR sequences.
Collaboratively Improving Topic Discovery and Word Embeddings by Coordinating Global and Local Contexts
This paper empirically shows that by incorporating both global and local context, this collaborative model can not only significantly improve the performance of topic discovery over the baseline topic models, but also learn better word embeddings than the baseline word embedding models.
DeepFusion: A Deep Learning Framework for the Fusion of Heterogeneous Sensory Data
DeepFusion, a unified multi-sensor deep learning framework, can combine different sensors' information weighted by the quality of their data and incorporate cross-s sensor correlations, and thus can benefit a wide spectrum of IoT applications.
DeepMV: Multi-View Deep Learning for Device-Free Human Activity Recognition
This poster presents a probabilistic procedure to estimate the intensity of earthquake-triggered landslides in China over a 25-year period from 1991 to 2002.
Deconfounding with Networked Observational Data in a Dynamic Environment
A novel ITE estimation framework Dynamic Networked Observational Data Deconfounder (\mymodel) is proposed which aims to learn representations of hidden confounders over time by leveraging both current networked observational data and historical information.
Personalized disease prediction using a CNN-based similarity learning method
- Qiuling Suo, Fenglong Ma, Jing Gao
- Computer ScienceIEEE International Conference on Bioinformatics…
- 1 November 2017
A novel time fusion CNN framework is built to simultaneously learn patient representations and measure pairwise similarity, and performs personalized disease predictions, and compares the effect of different vector representations and similarity learning metrics.
A Multi-view Deep Learning Method for Epileptic Seizure Detection using Short-time Fourier Transform
A multi-view deep learning model to capture brain abnormality from multi-channel epileptic EEG signals for seizure detection and is effective in detecting epileptic seizure is proposed.