no code implementations • EMNLP (NLPOSS) 2020 • John Morris, Jin Yong Yoo, Yanjun Qi
TextAttack is an open-source Python toolkit for adversarial attacks, adversarial training, and data augmentation in NLP.
no code implementations • 9 Apr 2024 • Dmitriy Bespalov, Sourav Bhabesh, Yi Xiang, Liutong Zhou, Yanjun Qi
Recent NLP literature pays little attention to the robustness of toxicity language predictors, while these systems are most likely to be used in adversarial contexts.
no code implementations • 9 Apr 2024 • Tong Wang, Ninad Kulkarni, Yanjun Qi
Assessing the factual consistency of automatically generated texts in relation to source context is crucial for developing reliable natural language generation applications.
no code implementations • 27 Feb 2024 • Xi Fang, Weijie Xu, Fiona Anting Tan, Jiani Zhang, Ziqing Hu, Yanjun Qi, Scott Nickleach, Diego Socolinsky, Srinivasan Sengamedu, Christos Faloutsos
Recent breakthroughs in large language modeling have facilitated rigorous exploration of their application in diverse tasks related to tabular data modeling, such as prediction, tabular data synthesis, question answering, and table understanding.
no code implementations • 7 Dec 2023 • Zifan Xu, Haozhu Wang, Dmitriy Bespalov, Peter Stone, Yanjun Qi
Simultaneously, RSD learns a reasoning policy to determine the required reasoning skill for a given question.
1 code implementation • 8 Jun 2023 • Hanyu Liu, Chengyuan Cai, Yanjun Qi
Most existing studies focused on designing attacks to evaluate the robustness of NLP models in the English language alone.
1 code implementation • 2 May 2023 • Zhe Wang, Jake Grigsby, Yanjun Qi
In this work, we develop a novel DG training strategy, we call PGrad, to learn a robust gradient direction, improving models' generalization ability on unseen domains.
1 code implementation • 3 Feb 2023 • Arshdeep Sekhon, Hanjie Chen, Aman Shrivastava, Zhe Wang, Yangfeng Ji, Yanjun Qi
Recent NLP literature has seen growing interest in improving model interpretability.
no code implementations • 1 Dec 2022 • Vanamala Venkataswamy, Jake Grigsby, Andrew Grimshaw, Yanjun Qi
We utilize Offline RL as a launchpad to learn effective scheduling policies from prior experience collected using Oracle or heuristic policies.
1 code implementation • 22 Nov 2022 • Paola Cascante-Bonilla, Leonid Karlinsky, James Seale Smith, Yanjun Qi, Vicente Ordonez
Generalized Zero-Shot Learning (GZSL) aims to train a classifier that can generalize to unseen classes, using a set of attributes as auxiliary information, and the visual features extracted from a pre-trained convolutional neural network.
no code implementations • 10 Nov 2022 • Vanamala Venkataswamy, Jake Grigsby, Andrew Grimshaw, Yanjun Qi
Finally, we demonstrate that the DRL scheduler can learn from and improve upon existing heuristic policies using Offline Learning.
no code implementations • Findings (NAACL) 2022 • Arshdeep Sekhon, Yangfeng Ji, Matthew B. Dwyer, Yanjun Qi
Recent literature has seen growing interest in using black-box strategies like CheckList for testing the behavior of NLP models.
no code implementations • 29 Oct 2021 • Aman Shrivastava, Yanjun Qi, Vicente Ordonez
Our empirical results show that MIMKD outperforms competing approaches across a wide range of student-teacher pairs with different capacities, with different architectures, and when student networks are with extremely low capacity.
3 code implementations • 10 Oct 2021 • Jake Grigsby, Yanjun Qi
A thorough investigation on a custom benchmark helps identify several key challenges involved in learning from high-noise datasets.
no code implementations • 27 Sep 2021 • Zhe Wang, Jake Grigsby, Arshdeep Sekhon, Yanjun Qi
This paper proposes a novel method, ST-MAML, that empowers model-agnostic meta-learning (MAML) to learn from multiple task distributions.
2 code implementations • 24 Sep 2021 • Jake Grigsby, Zhe Wang, Nam Nguyen, Yanjun Qi
Multivariate time series forecasting focuses on predicting future values based on historical context.
1 code implementation • Findings (EMNLP) 2021 • Jin Yong Yoo, Yanjun Qi
Adversarial training, a method for learning robust deep neural networks, constructs adversarial examples during training.
1 code implementation • EMNLP (BlackboxNLP) 2021 • Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon, Yangfeng Ji, Yanjun Qi
Via a small portion of word-level swaps, these adversarial perturbations aim to make the resulting text semantically and spatially similar to its seed input (therefore sharing similar interpretations).
no code implementations • 16 Jun 2021 • Paola Cascante-Bonilla, Arshdeep Sekhon, Yanjun Qi, Vicente Ordonez
This paper proposes PatchMix, a data augmentation method that creates new samples by composing patches from pairs of images in a grid-like pattern.
1 code implementation • 16 Jun 2021 • Jake Grigsby, Jin Yong Yoo, Yanjun Qi
Model-free off-policy actor-critic methods are an efficient solution to complex continuous control tasks.
no code implementations • 3 Mar 2021 • Halie M. Rando, Nils Wellhausen, Soumita Ghosh, Alexandra J. Lee, Anna Ada Dattoli, Fengling Hu, James Brian Byrd, Diane N. Rafizadeh, Ronan Lordan, Yanjun Qi, Yuchen Sun, Christian Brueffer, Jeffrey M. Field, Marouen Ben Guebila, Nafisa M. Jadavji, Ashwin N. Skelly, Bharath Ramsundar, Jinhui Wang, Rishi Raj Goel, YoSon Park, the COVID-19 Review Consortium, Simina M. Boca, Anthony Gitter, Casey S. Greene
A number of potential therapeutics against SARS-CoV-2 and the resultant COVID-19 illness were rapidly identified, leading to a large number of clinical trials investigating a variety of possible therapeutic approaches being initiated early on in the pandemic.
no code implementations • 3 Mar 2021 • Arshdeep Sekhon, Zhe Wang, Yanjun Qi
Understanding relationships between feature variables is one important way humans use to make decisions.
1 code implementation • 1 Feb 2021 • Halie M. Rando, Adam L. MacLean, Alexandra J. Lee, Ronan Lordan, Sandipan Ray, Vikas Bansal, Ashwin N. Skelly, Elizabeth Sell, John J. Dziak, Lamonica Shinholster, Lucy D'Agostino McGowan, Marouen Ben Guebila, Nils Wellhausen, Sergey Knyazev, Simina M. Boca, Stephen Capone, Yanjun Qi, YoSon Park, Yuchen Sun, David Mai, Joel D. Boerckel, Christian Brueffer, James Brian Byrd, Jeremy P. Kamil, Jinhui Wang, Ryan Velazquez, Gregory L Szeto, John P. Barton, Rishi Raj Goel, Serghei Mangul, Tiago Lubiana, COVID-19 Review Consortium, Anthony Gitter, Casey S. Greene
While this viral species was unknown prior to January 2020, its similarity to other coronaviruses that infect humans has allowed for rapid insight into the mechanisms that it uses to infect human hosts, as well as the ways in which the human immune system can respond.
2 code implementations • CVPR 2021 • Jack Lanchantin, Tianlu Wang, Vicente Ordonez, Yanjun Qi
Multi-label image classification is the task of predicting a set of labels corresponding to objects, attributes or other entities present in an image.
2 code implementations • 13 Oct 2020 • Jake Grigsby, Yanjun Qi
Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks.
2 code implementations • EMNLP (BlackboxNLP) 2020 • Jin Yong Yoo, John X. Morris, Eli Lifland, Yanjun Qi
We study the behavior of several black-box search algorithms used for generating adversarial examples for natural language processing (NLP) tasks.
2 code implementations • EMNLP 2020 • John X. Morris, Eli Lifland, Jin Yong Yoo, Jake Grigsby, Di Jin, Yanjun Qi
TextAttack also includes data augmentation and adversarial training modules for using components of adversarial attacks to improve model accuracy and robustness.
2 code implementations • Findings of the Association for Computational Linguistics 2020 • John X. Morris, Eli Lifland, Jack Lanchantin, Yangfeng Ji, Yanjun Qi
State-of-the-art attacks on NLP models lack a shared definition of a what constitutes a successful attack.
1 code implementation • 24 Apr 2020 • Arshdeep Sekhon, Zhe Wang, Yanjun Qi
Learning the differential statistical dependency network between two contexts is essential for many real-life applications, mostly in the high dimensional low sample regime.
1 code implementation • 16 Jan 2020 • Paola Cascante-Bonilla, Fuwen Tan, Yanjun Qi, Vicente Ordonez
Pseudo-labeling works by applying pseudo-labels to samples in the unlabeled set by using a model trained on the combination of the labeled samples and any previously pseudo-labeled samples, and iteratively repeating this process in a self-training cycle.
1 code implementation • ICLR 2019 • Jack Lanchantin, Arshdeep Sekhon, Yanjun Qi
We propose Label Message Passing (LaMP) Neural Networks to efficiently model the joint prediction of multiple labels.
1 code implementation • 10 Jul 2018 • Arshdeep Sekhon, Ritambhara Singh, Yanjun Qi
In this paper, we develop a novel attention-based deep learning architecture, DeepDiff, that provides a unified and end-to-end solution to model and to interpret how dependencies among histone modifications control the differential patterns of gene regulation.
2 code implementations • ICML 2018 • Beilun Wang, Arshdeep Sekhon, Yanjun Qi
We consider the problem of including additional knowledge in estimating sparse Gaussian graphical models (sGGMs) from aggregated samples, arising often in bioinformatics and neuroimaging applications.
2 code implementations • 13 Jan 2018 • Ji Gao, Jack Lanchantin, Mary Lou Soffa, Yanjun Qi
Although various techniques have been proposed to generate adversarial samples for white-box attacks on text, little attention has been paid to black-box attacks, which are more realistic scenarios.
2 code implementations • 30 Oct 2017 • Beilun Wang, Arshdeep Sekhon, Yanjun Qi
We focus on the problem of estimating the change in the dependency structures of two $p$-dimensional Gaussian Graphical models (GGMs).
no code implementations • ICLR 2018 • Jack Lanchantin, Arshdeep Sekhon, Ritambhara Singh, Yanjun Qi
In this paper, we propose a novel deep architecture, the Prototype Matching Network (PMN) to mimic the TF binding mechanisms.
2 code implementations • arXiv 2017 • Chandan Singh, Beilun Wang, Yanjun Qi
Determining functional brain connectivity is crucial to understanding the brain and neural differences underlying disorders such as autism.
1 code implementation • 1 Aug 2017 • Andrew P. Norton, Yanjun Qi
Due to the complex nature of deep learning, it is challenging to understand how deep models can be fooled by adversarial examples.
2 code implementations • NeurIPS 2017 • Ritambhara Singh, Jack Lanchantin, Arshdeep Sekhon, Yanjun Qi
This paper presents an attention-based deep learning approach; we call AttentiveChrome, that uses a unified architecture to model and to interpret dependencies among chromatin factors for controlling gene regulation.
1 code implementation • 6 Jun 2017 • Andrew Norton, Yanjun Qi
With growing interest in adversarial machine learning, it is important for machine learning practitioners and users to understand how their models may be attacked.
1 code implementation • 30 May 2017 • Weilin Xu, David Evans, Yanjun Qi
Feature squeezing is a recently-introduced framework for mitigating and detecting adversarial examples.
1 code implementation • 24 Apr 2017 • Ritambhara Singh, Arshdeep Sekhon, Kamran Kowsari, Jack Lanchantin, Beilun Wang, Yanjun Qi
This is because current gk-SK uses a trie-based algorithm to calculate co-occurrence of mismatched substrings resulting in a time cost proportional to $O(\Sigma^{M})$.
2 code implementations • Network and Distributed System Security Symposium 2018 • Weilin Xu, David Evans, Yanjun Qi
Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \emph{adversarial examples} that are generated by adding small but purposeful distortions to natural examples.
no code implementations • 22 Feb 2017 • Ji Gao, Beilun Wang, Zeming Lin, Weilin Xu, Yanjun Qi
By identifying and removing unnecessary features in a DNN model, DeepCloak limits the capacity an attacker can use generating adversarial samples and therefore increase the robustness against such inputs.
no code implementations • 22 Feb 2017 • Muthuraman Chidambaram, Yanjun Qi
The idea of style transfer has largely only been explored in image-based tasks, which we attribute in part to the specific nature of loss functions used for style transfer.
no code implementations • 22 Feb 2017 • Jack Lanchantin, Ritambhara Singh, Yanjun Qi
When analyzing the genome, researchers have discovered that proteins bind to DNA based on certain patterns of the DNA sequence known as "motifs".
2 code implementations • 9 Feb 2017 • Beilun Wang, Ji Gao, Yanjun Qi
Estimating multiple sparse Gaussian Graphical Models (sGGMs) jointly for many related tasks (large $K$) under a high-dimensional (large $p$) situation is an important task.
no code implementations • 1 Dec 2016 • Beilun Wang, Ji Gao, Yanjun Qi
Most machine learning classifiers, including deep neural networks, are vulnerable to adversarial examples.
1 code implementation • 12 Sep 2016 • Ritambhara Singh, Jack Lanchantin, Gabriel Robins, Yanjun Qi
Related methods in the literature fail to perform such predictions accurately, since they do not consider sample distribution shift of sequence segments from an annotated (source) context to an unannotated (target) context.
1 code implementation • 12 Aug 2016 • Jack Lanchantin, Ritambhara Singh, Beilun Wang, Yanjun Qi
In this paper, we propose a toolkit called the Deep Motif Dashboard (DeMo Dashboard) which provides a suite of visualization strategies to extract motifs, or sequence patterns from deep neural network models for TFBS classification.
1 code implementation • 7 Jul 2016 • Ritambhara Singh, Jack Lanchantin, Gabriel Robins, Yanjun Qi
To simultaneously visualize the combinatorial interactions among histone modifications, we propose a novel optimization-based technique that generates feature pattern maps from the learnt deep model.
1 code implementation • 11 May 2016 • Beilun Wang, Ritambhara Singh, Yanjun Qi
Computationally, this task can be formulated as jointly estimating multiple different, but related, sparse Undirected Graphical Models (UGM) from aggregated samples across several contexts.
3 code implementations • 10 May 2016 • Zeming Lin, Jack Lanchantin, Yanjun Qi
Predicting protein properties such as solvent accessibility and secondary structure from its primary amino acid sequence is an important task in bioinformatics.
3 code implementations • 4 May 2016 • Jack Lanchantin, Ritambhara Singh, Zeming Lin, Yanjun Qi
This paper applies a deep convolutional/highway MLP framework to classify genomic sequences on the transcription factor binding site task.
no code implementations • 20 Dec 2013 • Yunlong He, Koray Kavukcuoglu, Yun Wang, Arthur Szlam, Yanjun Qi
In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks.
no code implementations • NeurIPS 2012 • Yunlong He, Yanjun Qi, Koray Kavukcuoglu, Haesun Park
In this paper, we study latent factor models with the dependency structure in the latent space.
no code implementations • NeurIPS 2009 • Bing Bai, Jason Weston, David Grangier, Ronan Collobert, Kunihiko Sadamasa, Yanjun Qi, Corinna Cortes, Mehryar Mohri
We present a class of nonlinear (polynomial) models that are discriminatively trained to directly map from the word content in a query-document or document-document pair to a ranking score.