
A DataCentric Framework for Composable NLP Workflows
Empirical natural language processing (NLP) systems in application domai...
read it

Towards Robust Medical Image Segmentation on SmallScale Data with Incomplete Labels
The datadriven nature of deep learning models for semantic segmentation...
read it

Squared ℓ_2 Norm as Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations
Data augmentation is one of the most popular techniques for improving th...
read it

Iterative Graph SelfDistillation
How to discriminatively vectorize graphs is a fundamental challenge that...
read it

Word Shape Matters: Robust Machine Translation with Visual Embedding
Neural machine translation has achieved remarkable empirical performance...
read it

Summarizing Text on Any Aspects: A KnowledgeInformed WeaklySupervised Approach
Given a document and a target aspect (e.g., a topic of interest), aspect...
read it

SelfChallenging Improves CrossDomain Generalization
Convolutional Neural Networks (CNN) conduct image classification by acti...
read it

On Dropout, Overfitting, and Interaction Effects in Deep Neural Networks
We examine Dropout through the perspective of interactions: learned effe...
read it

Progressive Generation of Long Text
Largescale language models pretrained on massive corpora of text, such ...
read it

Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
Despite success on a wide range of problems related to vision, generativ...
read it

Distributed, partially collapsed MCMC for Bayesian Nonparametrics
Bayesian nonparametric (BNP) models provide elegant methods for discover...
read it

Learning Data Manipulation for Augmentation and Weighting
Manipulating data, such as weighting data examples or augmenting with ne...
read it

Learning SampleSpecific Models with LowRank Personalized Regression
Modern applications of machine learning (ML) deal with increasingly hete...
read it

Learning Sparse Nonparametric DAGs
We develop a framework for learning sparse nonparametric directed acycli...
read it

ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations
We describe ChemBO, a Bayesian Optimization framework for generating and...
read it

Learning Robust Global Representations by Penalizing Local Predictive Power
Despite their renowned predictive power on i.i.d. data, convolutional ne...
read it

High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
We investigate the relationship between the frequency spectrum of image ...
read it

Adversarial Domain Adaptation Being Aware of Class Relationships
Adversarial training is a useful approach to promote the learning of tra...
read it

TargetGuided OpenDomain Conversation
Many realworld opendomain conversation applications have specific goal...
read it

Knowledgedriven Encode, Retrieve, Paraphrase for Medical Image Report Generation
Generating long and semanticcoherent reports to describe medical images...
read it

Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly
Bayesian Optimisation (BO), refers to a suite of techniques for global o...
read it

Theoretically Principled Tradeoff between Robustness and Accuracy
We identify a tradeoff between robustness and accuracy that serves as a...
read it

Stackelberg GAN: Towards Provable Minimax Equilibrium via MultiGenerator Architectures
We study the problem of alleviating the instability issue in the GAN tra...
read it

Discourse in Multimedia: A Case Study in Information Extraction
To ensure readability, text is often written and presented with due form...
read it

Fault Tolerance in IterativeConvergent Machine Learning
Machine learning (ML) training algorithms often possess an inherent self...
read it

Toward Understanding the Impact of Staleness in Distributed Machine Learning
Many distributed machine learning (ML) systems adopt the nonsynchronous...
read it

Sample Complexity of Nonparametric SemiSupervised Learning
We study the sample complexity of semisupervised learning (SSL) and int...
read it

What If We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Tasks
Nature language inference (NLI) task is a predictive task of determining...
read it

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
We introduce Texar, an opensource toolkit aiming to support the broad s...
read it

Hybrid Subspace Learning for HighDimensional Data
The highdimensional data setting, in which p >> n, is a challenging sta...
read it

Reinforced AutoZoom Net: Towards Accurate and Fast Breast Cancer Segmentation in Wholeslide Images
Convolutional neural networks have led to significant breakthroughs in t...
read it

QueryConditioned ThreePlayer Adversarial Network for Video Summarization
Video summarization plays an important role in video understanding by se...
read it

Unsupervised Domain Adaptation for Automatic Estimation of Cardiothoracic Ratio
The cardiothoracic ratio (CTR), a clinical metric of heart size in chest...
read it

Unsupervised Text Style Transfer using Language Models as Discriminators
Binary classifiers are often employed as discriminators in GANbased uns...
read it

Rethinking Knowledge Graph Propagation for ZeroShot Learning
The potential of graph convolutional neural networks for the task of zer...
read it

Hybrid RetrievalGeneration Reinforced Agent for Medical Image Report Generation
Generating long and coherent reports to describe medical images poses ch...
read it

Imagederived generative modeling of pseudomacromolecular structures  towards the statistical assessment of Electron CryoTomography template matching
Cellular Electron CryoTomography (CECT) is a 3D imaging technique that c...
read it

DTRGAN: Dilated Temporal Relational Adversarial Network for Video Summarization
The large amount of videos popping up every day, make it is more and mor...
read it

ConnNet: A LongRange RelationAware PixelConnectivity Network for Salient Segmentation
Salient segmentation aims to segment out attentiongrabbing regions, a c...
read it

Fair Deep Learning Prediction for Healthcare Applications with Confounder Filtering
The rapid development of deep learning methods has permitted the fast an...
read it

DAGs with NO TEARS: Smooth Optimization for Structure Learning
Estimating the structure of directed acyclic graphs (DAGs, also known as...
read it

OrthogonalityPromoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis
Distance metric learning (DML), which learns a distance metric from labe...
read it

DiCE: The Infinitely Differentiable MonteCarlo Estimator
The score function estimator is widely used for estimating gradients of ...
read it

Identifiability of Nonparametric Mixture Models and Bayes Optimal Clustering
Motivated by problems in data clustering, we establish general condition...
read it

Transformation Autoregressive Networks
The fundamental task of general density estimation has been of keen inte...
read it

Personalized Survival Prediction with Contextual Explanation Networks
Accurate and transparent prediction of cancer survival times on the leve...
read it

The Intriguing Properties of Model Explanations
Linear approximations to the decision boundary of a complex model have b...
read it

Semanticaware GradGAN for VirtualtoReal Urban Scene Adaption
Recent advances in vision tasks (e.g., segmentation) highly depend on th...
read it

Unsupervised ObjectLevel Video Summarization with Online Motion AutoEncoder
Unsupervised video summarization plays an important role on digesting, b...
read it

Stability Selection for Structured Variable Selection
In variable or graph selection problems, finding a rightsized model or ...
read it
Eric P Xing
is this you? claim profile
Professor of Machine Learning, Language Technology, Computer Science, Cargenie Mellon University