2 code implementations • ICML 2020 • Zijun Zhang, Ruixiang Zhang, Zongpeng Li, Yoshua Bengio, Liam Paull
We therefore propose to map both the generated and target distributions to a latent space using the encoder of a standard autoencoder, and train the generator (or decoder) to match the target distribution in the latent space.
1 code implementation • 28 Feb 2023 • Luoxiao Yang, Xinqi Fan, Zijun Zhang
To address this challenge, this paper proposes a novel machine vision assisted deep time series analysis (MV-DTSA) framework.
1 code implementation • 20 Jan 2023 • Michail Chatzianastasis, Michalis Vazirgiannis, Zijun Zhang
Unlike conventional graph learning on a single biological network, EMGNN uses a multilayered graph neural network to learn from multiple biological networks for accurate cancer gene prediction.
1 code implementation • ICLR 2018 • Zijun Zhang, Lin Ma, Zongpeng Li, Chuan Wu
Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios.
2 code implementations • 19 Aug 2021 • Luoxiao Yang, Long Wang, Zijun Zhang
First, different from traditional studies regarding the WPC modeling as a curve fitting problem, in this paper, we renovate the WPC modeling formulation from a machine vision aspect.
1 code implementation • NeurIPS 2018 • Zijun Zhang, Yining Zhang, Zongpeng Li
Multiplicative noise, including dropout, is widely used to regularize deep neural networks (DNNs), and is shown to be effective in a wide range of architectures and tasks.
1 code implementation • 18 May 2023 • Zijun Zhang, Adam R. Lamson, Michael Shelley, Olga Troyanskaya
Creating predictive and interpretable models for these pathways is challenging because of the complexity of the pathways and of the cellular and genomic contexts.
1 code implementation • 12 Feb 2024 • Huixin Zhan, Ying Nian Wu, Zijun Zhang
Impressively, applying these adapters on natural language foundation models matched or even exceeded the performance of DNA foundation models.
1 code implementation • 1 Sep 2019 • Zijun Zhang, Linqi Zhou, Liangke Gou, Ying Nian Wu
We report a neural architecture search framework, BioNAS, that is tailored for biomedical researchers to easily build, evaluate, and uncover novel knowledge from interpretable deep learning models.
1 code implementation • 28 Sep 2023 • Christian Pedersen, Tiberiu Tesileanu, Tinghui Wu, Siavash Golkar, Miles Cranmer, Zijun Zhang, Shirley Ho
This suggests that different neural architectures are sensitive to different aspects of the data, an important yet under-explored challenge for clinical prediction tasks.
no code implementations • 5 Aug 2021 • Tiange Wang, Zijun Zhang, Kwok-Leung Tsui
Accurate forecasting of traffic conditions is critical for improving safety, stability, and efficiency of a city transportation system.
no code implementations • 5 Aug 2021 • Tiange Wang, Zijun Zhang, Fangfang Yang, Kwok-Leung Tsui
Most existing vision-based approaches focus on the detection of frontal intrusion objects with prior labels, such as categories and locations of the objects.
no code implementations • 5 Aug 2021 • Tiange Wang, Zijun Zhang, Fangfang Yang, Kwok-Leung Tsui
The automatic detection of major rail components using railway images is beneficial to ensure the rail transport safety.
no code implementations • 24 Mar 2022 • Luoxiao Yang, Zhong Zheng, Zijun Zhang
The convolutional neural network (CNN) has been widely applied to process the industrial data based tensor input, which integrates data records of distributed industrial systems from the spatial, temporal, and system dynamics aspects.
no code implementations • 6 Nov 2023 • Huixin Zhan, Zijun Zhang
Clinical variant classification of pathogenic versus benign genetic variants remains a pivotal challenge in clinical genetics.
no code implementations • 20 Feb 2024 • Junwei Su, Difan Zou, Zijun Zhang, Chuan Wu
We provide a formal formulation and analysis of the problem, and propose a novel regularization-based technique called Structural-Shift-Risk-Mitigation (SSRM) to mitigate the impact of the structural shift on catastrophic forgetting of the inductive NGIL problem.