Search Results for author: Yanjun Qi

Found 59 papers, 37 papers with code

TextAttack: Lessons learned in designing Python frameworks for NLP

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.

Adversarial Attack Data Augmentation

Securing the Future of GenAI: Policy and Technology

no code implementations21 May 2024 Mihai Christodorescu, Ryan Craven, Soheil Feizi, Neil Gong, Mia Hoffmann, Somesh Jha, Zhengyuan Jiang, Mehrdad Saberi Kamarposhti, John Mitchell, Jessica Newman, Emelia Probasco, Yanjun Qi, Khawaja Shams, Matthew Turek

The interplay between legislation and technology is a very vast topic, and we don't claim that this paper is a comprehensive treatment on this topic.

Towards Building a Robust Toxicity Predictor

no code implementations9 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.

Adversarial Attack

Less is More for Improving Automatic Evaluation of Factual Consistency

no code implementations9 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.

Language Modelling Large Language Model +1

Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey

1 code implementation27 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.

Language Modelling Navigate +1

Latent Skill Discovery for Chain-of-Thought Reasoning

no code implementations7 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.


Expanding Scope: Adapting English Adversarial Attacks to Chinese

1 code implementation8 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.

Adversarial Attack Adversarial Robustness +1

PGrad: Learning Principal Gradients For Domain Generalization

1 code implementation2 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.

Domain Generalization

Improving Interpretability via Explicit Word Interaction Graph Layer

1 code implementation3 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.

Launchpad: Learning to Schedule Using Offline and Online RL Methods

no code implementations1 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.

Offline RL reinforcement-learning +2

On the Transferability of Visual Features in Generalized Zero-Shot Learning

1 code implementation22 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.

Generalized Zero-Shot Learning Knowledge Distillation +2

RARE: Renewable Energy Aware Resource Management in Datacenters

no code implementations10 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.

Management Scheduling

White-box Testing of NLP models with Mask Neuron Coverage

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.

Data Augmentation Fault Detection

Estimating and Maximizing Mutual Information for Knowledge Distillation

no code implementations29 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.

Knowledge Distillation

A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets

3 code implementations10 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.

Decision Making reinforcement-learning +1

ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning

no code implementations27 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.

Diversity Few-Shot Image Classification +1

Long-Range Transformers for Dynamic Spatiotemporal Forecasting

2 code implementations24 Sep 2021 Jake Grigsby, Zhe Wang, Nam Nguyen, Yanjun Qi

Multivariate time series forecasting focuses on predicting future values based on historical context.

Multivariate Time Series Forecasting Time Series

Towards Improving Adversarial Training of NLP Models

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.

Domain Generalization Sentence

Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing

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).

Language Modelling

Evolving Image Compositions for Feature Representation Learning

no code implementations16 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.

Data Augmentation Representation Learning +1

Towards Automatic Actor-Critic Solutions to Continuous Control

1 code implementation16 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.

Continuous Control

Identification and Development of Therapeutics for COVID-19

no code implementations3 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.

Relate and Predict: Structure-Aware Prediction with Jointly Optimized Neural DAG

no code implementations3 Mar 2021 Arshdeep Sekhon, Zhe Wang, Yanjun Qi

Understanding relationships between feature variables is one important way humans use to make decisions.

General Multi-label Image Classification with Transformers

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.

Classification General Classification +1

Measuring Visual Generalization in Continuous Control from Pixels

2 code implementations13 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.

Continuous Control Data Augmentation +2

Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples

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.

Adversarial Text Benchmarking +1

TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

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.

Adversarial Text Data Augmentation +3

Beyond Data Samples: Aligning Differential Networks Estimation with Scientific Knowledge

1 code implementation24 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.

Network Identification Structured Prediction

Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning

1 code implementation16 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.

Image Classification

Neural Message Passing for Multi-Label Classification

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.

Classification General Classification +1

DeepDiff: Deep-learning for predicting Differential gene expression from histone modifications

1 code implementation10 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.

A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models

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.

2k Computational Efficiency +1

Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers

2 code implementations13 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.

Adversarial Text General Classification +4

Fast and Scalable Learning of Sparse Changes in High-Dimensional Gaussian Graphical Model Structure

2 code implementations30 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).

A Constrained, Weighted-L1 Minimization Approach for Joint Discovery of Heterogeneous Neural Connectivity Graphs

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.

Connectivity Estimation

Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning

1 code implementation1 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.

Adversarial Attack Adversarial Defense +1

Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin

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.

Adversarial-Playground: A Visualization Suite for Adversarial Sample Generation

1 code implementation6 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.

BIG-bench Machine Learning

Feature Squeezing Mitigates and Detects Carlini/Wagner Adversarial Examples

1 code implementation30 May 2017 Weilin Xu, David Evans, Yanjun Qi

Feature squeezing is a recently-introduced framework for mitigating and detecting adversarial examples.

GaKCo: a Fast GApped k-mer string Kernel using COunting

1 code implementation24 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 $O(\Sigma^{M})$.

Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks

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.

DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples

no code implementations22 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.

General Classification

Style Transfer Generative Adversarial Networks: Learning to Play Chess Differently

no code implementations22 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.

Attribute Style Transfer

Memory Matching Networks for Genomic Sequence Classification

no code implementations22 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".

Classification General Classification

A Fast and Scalable Joint Estimator for Learning Multiple Related Sparse Gaussian Graphical Models

2 code implementations9 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.

Computational Efficiency

A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples

no code implementations1 Dec 2016 Beilun Wang, Ji Gao, Yanjun Qi

Most machine learning classifiers, including deep neural networks, are vulnerable to adversarial examples.

Representation Learning

Transfer String Kernel for Cross-Context DNA-Protein Binding Prediction

1 code implementation12 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.

Transfer Learning

Deep Motif Dashboard: Visualizing and Understanding Genomic Sequences Using Deep Neural Networks

1 code implementation12 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.

General Classification

DeepChrome: Deep-learning for predicting gene expression from histone modifications

1 code implementation7 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.

A constrained L1 minimization approach for estimating multiple Sparse Gaussian or Nonparanormal Graphical Models

1 code implementation11 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.

MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction

3 code implementations10 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.

General Classification Image Classification +3

Deep Motif: Visualizing Genomic Sequence Classifications

3 code implementations4 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.

Unsupervised Feature Learning by Deep Sparse Coding

no code implementations20 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.

Object Recognition

Learning the Dependency Structure of Latent Factors

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.

Polynomial Semantic Indexing

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.


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