Search Results for author: Ricardo Henao

Found 67 papers, 28 papers with code

Few-Shot Class-Incremental Learning for Named Entity Recognition

no code implementations ACL 2022 Rui Wang, Tong Yu, Handong Zhao, Sungchul Kim, Subrata Mitra, Ruiyi Zhang, Ricardo Henao

In this work, we study a more challenging but practical problem, i. e., few-shot class-incremental learning for NER, where an NER model is trained with only few labeled samples of the new classes, without forgetting knowledge of the old ones.

class-incremental learning Few-Shot Class-Incremental Learning +4

Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity Recognition

no code implementations EMNLP 2021 Rui Wang, Ricardo Henao

Unsupervised consistency training is a way of semi-supervised learning that encourages consistency in model predictions between the original and augmented data.

Data Augmentation Low Resource Named Entity Recognition +4

An Effective Meaningful Way to Evaluate Survival Models

1 code implementation1 Jun 2023 Shi-ang Qi, Neeraj Kumar, Mahtab Farrokh, Weijie Sun, Li-Hao Kuan, Rajesh Ranganath, Ricardo Henao, Russell Greiner

One straightforward metric to evaluate a survival prediction model is based on the Mean Absolute Error (MAE) -- the average of the absolute difference between the time predicted by the model and the true event time, over all subjects.

Survival Prediction

Mitigating Test-Time Bias for Fair Image Retrieval

1 code implementation23 May 2023 Fanjie Kong, Shuai Yuan, Weituo Hao, Ricardo Henao

We address the challenge of generating fair and unbiased image retrieval results given neutral textual queries (with no explicit gender or race connotations), while maintaining the utility (performance) of the underlying vision-language (VL) model.

Image Retrieval Language Modelling +1

Open World Classification with Adaptive Negative Samples

no code implementations9 Mar 2023 Ke Bai, Guoyin Wang, Jiwei Li, Sunghyun Park, Sungjin Lee, Puyang Xu, Ricardo Henao, Lawrence Carin

Open world classification is a task in natural language processing with key practical relevance and impact.


Toward Fairness in Text Generation via Mutual Information Minimization based on Importance Sampling

no code implementations25 Feb 2023 Rui Wang, Pengyu Cheng, Ricardo Henao

To improve the fairness of PLMs in text generation, we propose to minimize the mutual information between the semantics in the generated text sentences and their demographic polarity, i. e., the demographic group to which the sentence is referring.

Fairness Language Modelling +1

Neural Insights for Digital Marketing Content Design

no code implementations2 Feb 2023 Fanjie Kong, Yuan Li, Tanner Fiez, Shreya Chakrabarti, Ricardo Henao, Houssam Nassif

In digital marketing, experimenting with new website content is one of the key levers to improve customer engagement.


Pushing the Efficiency Limit Using Structured Sparse Convolutions

no code implementations23 Oct 2022 Vinay Kumar Verma, Nikhil Mehta, Shijing Si, Ricardo Henao, Lawrence Carin

Weight pruning is among the most popular approaches for compressing deep convolutional neural networks.

Toward Sustainable Continual Learning: Detection and Knowledge Repurposing of Similar Tasks

no code implementations11 Oct 2022 Sijia Wang, Yoojin Choi, Junya Chen, Mostafa El-Khamy, Ricardo Henao

This results in the eventual prohibitive expansion of the knowledge repository if we consider learning from a long sequence of tasks.

Continual Learning

Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations

1 code implementation25 Feb 2022 Paidamoyo Chapfuwa, Sherri Rose, Lawrence Carin, Edward Meeds, Ricardo Henao

Understanding the effects of these system inputs on system outputs is crucial to have any meaningful model of a dynamical system.

Time Series Analysis

Flexible Triggering Kernels for Hawkes Process Modeling

1 code implementation3 Feb 2022 Yamac Alican Isik, Connor Davis, Paidamoyo Chapfuwa, Ricardo Henao

Recently proposed encoder-decoder structures for modeling Hawkes processes use transformer-inspired architectures, which encode the history of events via embeddings and self-attention mechanisms.

Gradient Importance Learning for Incomplete Observations

1 code implementation ICLR 2022 Qitong Gao, Dong Wang, Joshua D. Amason, Siyang Yuan, Chenyang Tao, Ricardo Henao, Majda Hadziahmetovic, Lawrence Carin, Miroslav Pajic

Though recent works have developed methods that can generate estimates (or imputations) of the missing entries in a dataset to facilitate downstream analysis, most depend on assumptions that may not align with real-world applications and could suffer from poor performance in subsequent tasks such as classification.

Imputation Reinforcement Learning (RL) +1

Efficient Classification of Very Large Images with Tiny Objects

1 code implementation CVPR 2022 Fanjie Kong, Ricardo Henao

Specifically, these classification tasks face two key challenges: $i$) the size of the input image is usually in the order of mega- or giga-pixels, however, existing deep architectures do not easily operate on such big images due to memory constraints, consequently, we seek a memory-efficient method to process these images; and $ii$) only a very small fraction of the input images are informative of the label of interest, resulting in low region of interest (ROI) to image ratio.

Classification Image Classification

SpanPredict: Extraction of Predictive Document Spans with Neural Attention

no code implementations NAACL 2021 Vivek Subramanian, Matthew Engelhard, Sam Berchuck, Liqun Chen, Ricardo Henao, Lawrence Carin

In many natural language processing applications, identifying predictive text can be as important as the predictions themselves.

Malignancy Prediction and Lesion Identification from Clinical Dermatological Images

no code implementations2 Apr 2021 Meng Xia, Meenal K. Kheterpal, Samantha C. Wong, Christine Park, William Ratliff, Lawrence Carin, Ricardo Henao

We consider machine-learning-based malignancy prediction and lesion identification from clinical dermatological images, which can be indistinctly acquired via smartphone or dermoscopy capture.

Quantum Tensor Network in Machine Learning: An Application to Tiny Object Classification

1 code implementation8 Jan 2021 Fanjie Kong, Xiao-Yang Liu, Ricardo Henao

In the end, our experimental results indicate that tensor network models are effective for tiny object classification problem and potentially will beat state-of-the-art.

BIG-bench Machine Learning Classification +3

Wasserstein Contrastive Representation Distillation

no code implementations CVPR 2021 Liqun Chen, Dong Wang, Zhe Gan, Jingjing Liu, Ricardo Henao, Lawrence Carin

The primary goal of knowledge distillation (KD) is to encapsulate the information of a model learned from a teacher network into a student network, with the latter being more compact than the former.

Contrastive Learning Knowledge Distillation +2

Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer

1 code implementation NeurIPS 2021 Zidi Xiu, Junya Chen, Ricardo Henao, Benjamin Goldstein, Lawrence Carin, Chenyang Tao

Dealing with severe class imbalance poses a major challenge for real-world applications, especially when the accurate classification and generalization of minority classes is of primary interest.

Inductive Bias Transfer Learning

Counterfactual Representation Learning with Balancing Weights

no code implementations23 Oct 2020 Serge Assaad, Shuxi Zeng, Chenyang Tao, Shounak Datta, Nikhil Mehta, Ricardo Henao, Fan Li, Lawrence Carin

A key to causal inference with observational data is achieving balance in predictive features associated with each treatment type.

Causal Inference Representation Learning

Variational Disentanglement for Rare Event Modeling

1 code implementation17 Sep 2020 Zidi Xiu, Chenyang Tao, Michael Gao, Connor Davis, Benjamin A. Goldstein, Ricardo Henao

Combining the increasing availability and abundance of healthcare data and the current advances in machine learning methods have created renewed opportunities to improve clinical decision support systems.

Disentanglement imbalanced classification +1

Adaptive multi-channel event segmentation and feature extraction for monitoring health outcomes

no code implementations20 Aug 2020 Xichen She, Yaya Zhai, Ricardo Henao, Christopher W. Woods, Christopher Chiu, Geoffrey S. Ginsburg, Peter X. K. Song, Alfred O. Hero

$\textbf{Conclusion}$: The proposed transfer learning event segmentation method is robust to temporal shifts in data distribution and can be used to produce highly discriminative event-labeled features for health monitoring.

Event Segmentation Transfer Learning

Weakly supervised cross-domain alignment with optimal transport

no code implementations14 Aug 2020 Siyang Yuan, Ke Bai, Liqun Chen, Yizhe Zhang, Chenyang Tao, Chunyuan Li, Guoyin Wang, Ricardo Henao, Lawrence Carin

Cross-domain alignment between image objects and text sequences is key to many visual-language tasks, and it poses a fundamental challenge to both computer vision and natural language processing.

Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage

1 code implementation22 Jun 2020 Shijing Si, Rui Wang, Jedrek Wosik, Hao Zhang, David Dov, Guoyin Wang, Ricardo Henao, Lawrence Carin

Small and imbalanced datasets commonly seen in healthcare represent a challenge when training classifiers based on deep learning models.

Neural Conditional Event Time Models

no code implementations3 Apr 2020 Matthew Engelhard, Samuel Berchuck, Joshua D'Arcy, Ricardo Henao

Consequently, no distinction is made between a) the probability of event occurrence, and b) the predicted time of occurrence.

Variational Learning of Individual Survival Distributions

1 code implementation9 Mar 2020 Zidi Xiu, Chenyang Tao, Benjamin A. Goldstein, Ricardo Henao

The abundance of modern health data provides many opportunities for the use of machine learning techniques to build better statistical models to improve clinical decision making.

Decision Making Survival Analysis +1

Survival Cluster Analysis

1 code implementation29 Feb 2020 Paidamoyo Chapfuwa, Chunyuan Li, Nikhil Mehta, Lawrence Carin, Ricardo Henao

As a result, there is an unmet need in survival analysis for identifying subpopulations with distinct risk profiles, while jointly accounting for accurate individualized time-to-event predictions.

Survival Analysis

Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes

no code implementations12 Feb 2020 Rachel Lea Draelos, David Dov, Maciej A. Mazurowski, Joseph Y. Lo, Ricardo Henao, Geoffrey D. Rubin, Lawrence Carin

This model reached a classification performance of AUROC greater than 0. 90 for 18 abnormalities, with an average AUROC of 0. 773 for all 83 abnormalities, demonstrating the feasibility of learning from unfiltered whole volume CT data.

BIG-bench Machine Learning Computed Tomography (CT) +1

Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods

1 code implementation NeurIPS 2019 Kevin J Liang, Guoyin Wang, Yitong Li, Ricardo Henao, Lawrence Carin

We investigate time-dependent data analysis from the perspective of recurrent kernel machines, from which models with hidden units and gated memory cells arise naturally.

Straight-Through Estimator as Projected Wasserstein Gradient Flow

no code implementations5 Oct 2019 Pengyu Cheng, Chang Liu, Chunyuan Li, Dinghan Shen, Ricardo Henao, Lawrence Carin

The Straight-Through (ST) estimator is a widely used technique for back-propagating gradients through discrete random variables.

Discriminative Clustering for Robust Unsupervised Domain Adaptation

no code implementations30 May 2019 Rui Wang, Guoyin Wang, Ricardo Henao

Unsupervised domain adaptation seeks to learn an invariant and discriminative representation for an unlabeled target domain by leveraging the information of a labeled source dataset.

Partial Domain Adaptation Unsupervised Domain Adaptation

Survival Function Matching for Calibrated Time-to-Event Predictions

1 code implementation21 May 2019 Paidamoyo Chapfuwa, Chenyang Tao, Lawrence Carin, Ricardo Henao

We present a survival function estimator for probabilistic predictions in time-to-event models, based on a neural network model for draws from the distribution of event times, without explicit assumptions on the form of the distribution.

Thyroid Cancer Malignancy Prediction From Whole Slide Cytopathology Images

no code implementations29 Mar 2019 David Dov, Shahar Kovalsky, Jonathan Cohen, Danielle Range, Ricardo Henao, Lawrence Carin

We consider preoperative prediction of thyroid cancer based on ultra-high-resolution whole-slide cytopathology images.

Multiple Instance Learning

Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment

no code implementations EMNLP 2018 Dinghan Shen, Xinyuan Zhang, Ricardo Henao, Lawrence Carin

Network embeddings, which learn low-dimensional representations for each vertex in a large-scale network, have received considerable attention in recent years.

Link Prediction Network Embedding +1

Hierarchical infinite factor model for improving the prediction of surgical complications for geriatric patients

1 code implementation24 Jul 2018 Elizabeth Lorenzi, Ricardo Henao, Katherine Heller

We develop a hierarchical infinite latent factor model (HIFM) to appropriately account for the covariance structure across subpopulations in data.


Variational Inference and Model Selection with Generalized Evidence Bounds

no code implementations ICML 2018 Liqun Chen, Chenyang Tao, Ruiyi Zhang, Ricardo Henao, Lawrence Carin Duke

Recent advances on the scalability and flexibility of variational inference have made it successful at unravelling hidden patterns in complex data.

Model Selection Variational Inference

Chi-square Generative Adversarial Network

1 code implementation ICML 2018 Chenyang Tao, Liqun Chen, Ricardo Henao, Jianfeng Feng, Lawrence Carin Duke

To assess the difference between real and synthetic data, Generative Adversarial Networks (GANs) are trained using a distribution discrepancy measure.

JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets

2 code implementations ICML 2018 Yunchen Pu, Shuyang Dai, Zhe Gan, Wei-Yao Wang, Guoyin Wang, Yizhe Zhang, Ricardo Henao, Lawrence Carin

Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains).

Joint Embedding of Words and Labels for Text Classification

2 code implementations ACL 2018 Guoyin Wang, Chunyuan Li, Wenlin Wang, Yizhe Zhang, Dinghan Shen, Xinyuan Zhang, Ricardo Henao, Lawrence Carin

Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences.

General Classification Sentiment Analysis +2

Adversarial Time-to-Event Modeling

4 code implementations ICML 2018 Paidamoyo Chapfuwa, Chenyang Tao, Chunyuan Li, Courtney Page, Benjamin Goldstein, Lawrence Carin, Ricardo Henao

Modern health data science applications leverage abundant molecular and electronic health data, providing opportunities for machine learning to build statistical models to support clinical practice.

Survival Analysis

Multi-Label Learning from Medical Plain Text with Convolutional Residual Models

no code implementations15 Jan 2018 Xinyuan Zhang, Ricardo Henao, Zhe Gan, Yitong Li, Lawrence Carin

Since diagnoses are typically correlated, a deep residual network is employed on top of the CNN encoder, to capture label (diagnosis) dependencies and incorporate information directly from the encoded sentence vector.

General Classification Multi-Label Classification +3

On the Use of Word Embeddings Alone to Represent Natural Language Sequences

no code implementations ICLR 2018 Dinghan Shen, Guoyin Wang, Wenlin Wang, Martin Renqiang Min, Qinliang Su, Yizhe Zhang, Ricardo Henao, Lawrence Carin

In this paper, we conduct an extensive comparative study between Simple Word Embeddings-based Models (SWEMs), with no compositional parameters, relative to employing word embeddings within RNN/CNN-based models.

Word Embeddings

Adversarial Symmetric Variational Autoencoder

no code implementations NeurIPS 2017 Yunchen Pu, Wei-Yao Wang, Ricardo Henao, Liqun Chen, Zhe Gan, Chunyuan Li, Lawrence Carin

A new form of variational autoencoder (VAE) is developed, in which the joint distribution of data and codes is considered in two (symmetric) forms: ($i$) from observed data fed through the encoder to yield codes, and ($ii$) from latent codes drawn from a simple prior and propagated through the decoder to manifest data.

Deconvolutional Latent-Variable Model for Text Sequence Matching

no code implementations21 Sep 2017 Dinghan Shen, Yizhe Zhang, Ricardo Henao, Qinliang Su, Lawrence Carin

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives.

Text Matching

ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching

5 code implementations NeurIPS 2017 Chunyuan Li, Hao liu, Changyou Chen, Yunchen Pu, Liqun Chen, Ricardo Henao, Lawrence Carin

We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching.

Deconvolutional Paragraph Representation Learning

4 code implementations NeurIPS 2017 Yizhe Zhang, Dinghan Shen, Guoyin Wang, Zhe Gan, Ricardo Henao, Lawrence Carin

Learning latent representations from long text sequences is an important first step in many natural language processing applications.

General Classification Representation Learning +1

Stochastic Gradient Monomial Gamma Sampler

no code implementations ICML 2017 Yizhe Zhang, Changyou Chen, Zhe Gan, Ricardo Henao, Lawrence Carin

A framework is proposed to improve the sampling efficiency of stochastic gradient MCMC, based on Hamiltonian Monte Carlo.

VAE Learning via Stein Variational Gradient Descent

no code implementations NeurIPS 2017 Yunchen Pu, Zhe Gan, Ricardo Henao, Chunyuan Li, Shaobo Han, Lawrence Carin

A new method for learning variational autoencoders (VAEs) is developed, based on Stein variational gradient descent.

Transfer Learning via Latent Factor Modeling to Improve Prediction of Surgical Complications

no code implementations2 Dec 2016 Elizabeth C Lorenzi, Zhifei Sun, Erich Huang, Ricardo Henao, Katherine A. Heller

We aim to create a framework for transfer learning using latent factor models to learn the dependence structure between a larger source dataset and a target dataset.

Transfer Learning

Learning Generic Sentence Representations Using Convolutional Neural Networks

no code implementations EMNLP 2017 Zhe Gan, Yunchen Pu, Ricardo Henao, Chunyuan Li, Xiaodong He, Lawrence Carin

We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes.

Towards Unifying Hamiltonian Monte Carlo and Slice Sampling

no code implementations NeurIPS 2016 Yizhe Zhang, Xiangyu Wang, Changyou Chen, Ricardo Henao, Kai Fan, Lawrence Carin

We unify slice sampling and Hamiltonian Monte Carlo (HMC) sampling, demonstrating their connection via the Hamiltonian-Jacobi equation from Hamiltonian mechanics.

Learning a Hybrid Architecture for Sequence Regression and Annotation

no code implementations16 Dec 2015 Yizhe Zhang, Ricardo Henao, Lawrence Carin, Jianling Zhong, Alexander J. Hartemink

When learning a hidden Markov model (HMM), sequen- tial observations can often be complemented by real-valued summary response variables generated from the path of hid- den states.


Deep Poisson Factor Modeling

no code implementations NeurIPS 2015 Ricardo Henao, Zhe Gan, James Lu, Lawrence Carin

We propose a new deep architecture for topic modeling, based on Poisson Factor Analysis (PFA) modules.

Topic Models

Bayesian Nonlinear Support Vector Machines and Discriminative Factor Modeling

no code implementations NeurIPS 2014 Ricardo Henao, Xin Yuan, Lawrence Carin

A new Bayesian formulation is developed for nonlinear support vector machines (SVMs), based on a Gaussian process and with the SVM hinge loss expressed as a scaled mixture of normals.

Bayesian Sparse Factor Models and DAGs Inference and Comparison

no code implementations NeurIPS 2009 Ricardo Henao, Ole Winther

In this paper we present a novel approach to learn directed acyclic graphs (DAG) and factor models within the same framework while also allowing for model comparison between them.

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