Search Results for author: Qicheng Lao

Found 11 papers, 2 papers with code

FlowX: Towards Explainable Graph Neural Networks via Message Flows

no code implementations26 Jun 2022 Shurui Gui, Hao Yuan, Jie Wang, Qicheng Lao, Kang Li, Shuiwang Ji

We investigate the explainability of graph neural networks (GNNs) as a step towards elucidating their working mechanisms.

Philosophy

Towards Adversarial Robustness via Transductive Learning

no code implementations15 Jun 2021 Jiefeng Chen, Yang Guo, Xi Wu, Tianqi Li, Qicheng Lao, YIngyu Liang, Somesh Jha

Compared to traditional "test-time" defenses, these defense mechanisms "dynamically retrain" the model based on test time input via transductive learning; and theoretically, attacking these defenses boils down to bilevel optimization, which seems to raise the difficulty for adaptive attacks.

Adversarial Robustness Bilevel Optimization

Test-Time Adaptation and Adversarial Robustness

no code implementations1 Jan 2021 Xi Wu, Yang Guo, Tianqi Li, Jiefeng Chen, Qicheng Lao, YIngyu Liang, Somesh Jha

On the positive side, we show that, if one is allowed to access the training data, then Domain Adversarial Neural Networks (${\sf DANN}$), an algorithm designed for unsupervised domain adaptation, can provide nontrivial robustness in the test-time maximin threat model against strong transfer attacks and adaptive fixed point attacks.

Adversarial Robustness Unsupervised Domain Adaptation

Hypothesis Disparity Regularized Mutual Information Maximization

no code implementations15 Dec 2020 Qicheng Lao, Xiang Jiang, Mohammad Havaei

We propose a hypothesis disparity regularized mutual information maximization~(HDMI) approach to tackle unsupervised hypothesis transfer -- as an effort towards unifying hypothesis transfer learning (HTL) and unsupervised domain adaptation (UDA) -- where the knowledge from a source domain is transferred solely through hypotheses and adapted to the target domain in an unsupervised manner.

Unsupervised Domain Adaptation

Conditional Generation of Medical Images via Disentangled Adversarial Inference

no code implementations8 Dec 2020 Mohammad Havaei, Ximeng Mao, Yiping Wang, Qicheng Lao

Current practices in using cGANs for medical image generation, only use a single variable for image generation (i. e., content) and therefore, do not provide much flexibility nor control over the generated image.

Data Augmentation Disentanglement +2

Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation

1 code implementation ICML 2020 Xiang Jiang, Qicheng Lao, Stan Matwin, Mohammad Havaei

We present an approach for unsupervised domain adaptation---with a strong focus on practical considerations of within-domain class imbalance and between-domain class distribution shift---from a class-conditioned domain alignment perspective.

pseudo label Unsupervised Domain Adaptation

FoCL: Feature-Oriented Continual Learning for Generative Models

1 code implementation9 Mar 2020 Qicheng Lao, Mehrzad Mortazavi, Marzieh Tahaei, Francis Dutil, Thomas Fevens, Mohammad Havaei

In this paper, we propose a general framework in continual learning for generative models: Feature-oriented Continual Learning (FoCL).

Continual Learning Incremental Learning

Case-Based Histopathological Malignancy Diagnosis using Convolutional Neural Networks

no code implementations28 May 2019 Qicheng Lao, Thomas Fevens

In practice, histopathological diagnosis of tumor malignancy often requires a human expert to scan through histopathological images at multiple magnification levels, after which a final diagnosis can be accurately determined.

General Classification

Leveraging Disease Progression Learning for Medical Image Recognition

no code implementations26 Jun 2018 Qicheng Lao, Thomas Fevens, Boyu Wang

Unlike natural images, medical images often have intrinsic characteristics that can be leveraged for neural network learning.

Cannot find the paper you are looking for? You can Submit a new open access paper.