Search Results for author:
Found 224 papers, 60 papers with code
Learning Task Sampling Policy for Multitask Learning
It has been shown that training multi-task models with auxiliary tasks can improve the target task quality through cross-task transfer.
What Makes Good In-Context Examples for GPT-3?
In this work, we investigate whether there are more effective strategies for judiciously selecting in-context examples (relative to random sampling) that better leverage GPT-3’s in-context learning capabilities. Inspired by the recent success of leveraging a retrieval module to augment neural networks, we propose to retrieve examples that are semantically-similar to a test query sample to formulate its corresponding prompt.
Natural Language Understanding
Open-Domain Question Answering
+2
Methods for Numeracy-Preserving Word Embeddings
We propose a new methodology to assign and learn embeddings for numbers.
An Embedding Model for Estimating Legislative Preferences from the Frequency and Sentiment of Tweets
Legislator preferences are typically represented as measures of general ideology estimated from roll call votes on legislation, potentially masking important nuances in legislators{'} political attitudes.
Open World Classification with Adaptive Negative Samples
Open world classification is a task in natural language processing with key practical relevance and impact.
Pushing the Efficiency Limit Using Structured Sparse Convolutions
Weight pruning is among the most popular approaches for compressing deep convolutional neural networks.
Pseudo-OOD training for robust language models
The model is fine-tuned by introducing a new regularization loss that separates the embeddings of IND and OOD data, which leads to significant gains on the OOD prediction task during testing.
Collaborative Anomaly Detection
In recommendation systems, items are likely to be exposed to various users and we would like to learn about the familiarity of a new user with an existing item.
Improving Downstream Task Performance by Treating Numbers as Entities
Numbers are essential components of text, like any other word tokens, from which natural language processing (NLP) models are built and deployed.
elBERto: Self-supervised Commonsense Learning for Question Answering
Commonsense question answering requires reasoning about everyday situations and causes and effects implicit in context.
Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations
Understanding the effects of these system inputs on system outputs is crucial to have any meaningful model of a dynamical system.
Explainable multiple abnormality classification of chest CT volumes
We introduce the challenging new task of explainable multiple abnormality classification in volumetric medical images, in which a model must indicate the regions used to predict each abnormality.
Finite-Time Consensus Learning for Decentralized Optimization with Nonlinear Gossiping
Distributed learning has become an integral tool for scaling up machine learning and addressing the growing need for data privacy.
Variational Inference with Holder Bounds
In this work, we present a careful analysis of the thermodynamic variational objective (TVO), bridging the gap between existing variational objectives and shedding new insights to advance the field.
Hölder Bounds for Sensitivity Analysis in Causal Reasoning
We examine interval estimation of the effect of a treatment T on an outcome Y given the existence of an unobserved confounder U.
Gradient Importance Learning for Incomplete Observations
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.
Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization
Successful applications of InfoNCE and its variants have popularized the use of contrastive variational mutual information (MI) estimators in machine learning.
Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE
InfoNCE-based contrastive representation learners, such as SimCLR, have been tremendously successful in recent years.
SpanPredict: Extraction of Predictive Document Spans with Neural Attention
In many natural language processing applications, identifying predictive text can be as important as the predictions themselves.
Towards Fair Federated Learning with Zero-Shot Data Augmentation
Federated learning has emerged as an important distributed learning paradigm, where a server aggregates a global model from many client-trained models while having no access to the client data.
Malignancy Prediction and Lesion Identification from Clinical Dermatological Images
We consider machine-learning-based malignancy prediction and lesion identification from clinical dermatological images, which can be indistinctly acquired via smartphone or dermoscopy capture.
Efficient Feature Transformations for Discriminative and Generative Continual Learning
However, the growth in the number of additional parameters of many of these types of methods can be computationally expensive at larger scales, at times prohibitively so.
Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker.
FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders
Pretrained text encoders, such as BERT, have been applied increasingly in various natural language processing (NLP) tasks, and have recently demonstrated significant performance gains.
CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
Our approach is based on learning a set of global and task-specific parameters.
Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning
Zero-shot learning (ZSL) has been shown to be a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges still remain.
FLOP: Federated Learning on Medical Datasets using Partial Networks
While different data-driven deep learning models have been developed to mitigate the diagnosis of COVID-19, the data itself is still scarce due to patient privacy concerns.
What Makes Good In-Context Examples for GPT-$3$?
Inspired by the recent success of leveraging a retrieval module to augment large-scale neural network models, we propose to retrieve examples that are semantically-similar to a test sample to formulate its corresponding prompt.
Reinforcement Learning for Flexibility Design Problems
Flexibility design problems are a class of problems that appear in strategic decision-making across industries, where the objective is to design a ($e. g.$, manufacturing) network that affords flexibility and adaptivity.
Towards Robust and Efficient Contrastive Textual Representation Learning
There has been growing interest in representation learning for text data, based on theoretical arguments and empirical evidence.
Wasserstein Contrastive Representation Distillation
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.
Ranked #4 on
Knowledge Distillation
on CIFAR-100
Learning Graphons via Structured Gromov-Wasserstein Barycenters
Accordingly, given a set of graphs generated by an underlying graphon, we learn the corresponding step function as the Gromov-Wasserstein barycenter of the given graphs.
Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models
Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts.
AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning
Synchronization is a key step in data-parallel distributed machine learning (ML).
Reconsidering Generative Objectives For Counterfactual Reasoning
As a step towards more flexible, scalable and accurate ITE estimation, we present a novel generative Bayesian estimation framework that integrates representation learning, adversarial matching and causal estimation.
Calibrating CNNs for Lifelong Learning
Further, our approach does not require storing data samples from the old tasks, which is done by many replay based methods.
Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer
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.
Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks
Explanation methods facilitate the development of models that learn meaningful concepts and avoid exploiting spurious correlations.
Integrating Task Specific Information into Pretrained Language Models for Low Resource Fine Tuning
Pretrained Language Models (PLMs) have improved the performance of natural language understanding in recent years.
MixKD: Towards Efficient Distillation of Large-scale Language Models
Large-scale language models have recently demonstrated impressive empirical performance.
Semantic Matching for Sequence-to-Sequence Learning
In sequence-to-sequence models, classical optimal transport (OT) can be applied to semantically match generated sentences with target sentences.
Counterfactual Representation Learning with Balancing Weights
A key to causal inference with observational data is achieving balance in predictive features associated with each treatment type.
Double Robust Representation Learning for Counterfactual Prediction
Causal inference, or counterfactual prediction, is central to decision making in healthcare, policy and social sciences.
RetiNerveNet: Using Recursive Deep Learning to Estimate Pointwise 24-2 Visual Field Data based on Retinal Structure
Due to the SAP test's innate difficulty and its high test-retest variability, we propose the RetiNerveNet, a deep convolutional recursive neural network for obtaining estimates of the SAP visual field.
Improving Text Generation with Student-Forcing Optimal Transport
An extension is further proposed to improve the OT learning, based on the structural and contextual information of the text sequences.
Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images
The data sources described earlier make two "domains": a hand-collected data domain of images with threats, and a real-world domain of images assumed without threats.
Weakly supervised cross-domain alignment with optimal transport
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.
WAFFLe: Weight Anonymized Factorization for Federated Learning
Experiments on MNIST, FashionMNIST, and CIFAR-10 demonstrate WAFFLe's significant improvement to local test performance and fairness while simultaneously providing an extra layer of security.
Bridging Maximum Likelihood and Adversarial Learning via $α$-Divergence
Maximum likelihood (ML) and adversarial learning are two popular approaches for training generative models, and from many perspectives these techniques are complementary.
Graph Optimal Transport for Cross-Domain Alignment
In GOT, cross-domain alignment is formulated as a graph matching problem, by representing entities into a dynamically-constructed graph.
CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
In this paper, we propose a novel Contrastive Log-ratio Upper Bound (CLUB) of mutual information.
Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage
Small and imbalanced datasets commonly seen in healthcare represent a challenge when training classifiers based on deep learning models.
GO Hessian for Expectation-Based Objectives
An unbiased low-variance gradient estimator, termed GO gradient, was proposed recently for expectation-based objectives $\mathbb{E}_{q_{\boldsymbol{\gamma}}(\boldsymbol{y})} [f(\boldsymbol{y})]$, where the random variable (RV) $\boldsymbol{y}$ may be drawn from a stochastic computation graph with continuous (non-reparameterizable) internal nodes and continuous/discrete leaves.
Enabling Counterfactual Survival Analysis with Balanced Representations
Balanced representation learning methods have been applied successfully to counterfactual inference from observational data.
GAN Memory with No Forgetting
As a fundamental issue in lifelong learning, catastrophic forgetting is directly caused by inaccessible historical data; accordingly, if the data (information) were memorized perfectly, no forgetting should be expected.
Scalable Control Variates for Monte Carlo Methods via Stochastic Optimization
Control variates are a well-established tool to reduce the variance of Monte Carlo estimators.
Towards Understanding Fast Adversarial Training
Current neural-network-based classifiers are susceptible to adversarial examples.
Hierarchical Optimal Transport for Robust Multi-View Learning
Traditional multi-view learning methods often rely on two assumptions: ($i$) the samples in different views are well-aligned, and ($ii$) their representations in latent space obey the same distribution.
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance
Learning disentangled representations of natural language is essential for many NLP tasks, e. g., conditional text generation, style transfer, personalized dialogue systems, etc.
Y-Net for Chest X-Ray Preprocessing: Simultaneous Classification of Geometry and Segmentation of Annotations
A modified Y-Net architecture based on the VGG11 encoder is used to simultaneously learn geometric orientation (similarity transform parameters) of the chest and segmentation of radiographic annotations.
Reward Constrained Interactive Recommendation with Natural Language Feedback
Text-based interactive recommendation provides richer user feedback and has demonstrated advantages over traditional interactive recommender systems.
Improving Adversarial Text Generation by Modeling the Distant Future
Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation.
RaCT: Toward Amortized Ranking-Critical Training For Collaborative Filtering
We investigate new methods for training collaborative filtering models based on actor-critic reinforcement learning, to more directly maximize ranking-based objective functions.
APo-VAE: Text Generation in Hyperbolic Space
In this paper, we investigate text generation in a hyperbolic latent space to learn continuous hierarchical representations.
Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability
We consider the blackbox transfer-based targeted adversarial attack threat model in the realm of deep neural network (DNN) image classifiers.
Transferable Perturbations of Deep Feature Distributions
Almost all current adversarial attacks of CNN classifiers rely on information derived from the output layer of the network.
Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors
Naively trained neural networks tend to experience catastrophic forgetting in sequential task settings, where data from previous tasks are unavailable.
Towards Practical Lottery Ticket Hypothesis for Adversarial Training
Recent research has proposed the lottery ticket hypothesis, suggesting that for a deep neural network, there exist trainable sub-networks performing equally or better than the original model with commensurate training steps.
Survival Cluster Analysis
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.
On Leveraging Pretrained GANs for Generation with Limited Data
Demonstrated by natural-image generation, we reveal that low-level filters (those close to observations) of both the generator and discriminator of pretrained GANs can be transferred to facilitate generation in a perceptually-distinct target domain with limited training data.
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
By training on a large amount of image-text-action triplets in a self-supervised learning manner, the pre-trained model provides generic representations of visual environments and language instructions.
Ranked #1 on
Visual Navigation
on Help, Anna! (HANNA)
Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes
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.
Object Detection as a Positive-Unlabeled Problem
These missing annotations can be problematic, as the standard cross-entropy loss employed to train object detection models treats classification as a positive-negative (PN) problem: unlabeled regions are implicitly assumed to be background.
Learning Autoencoders with Relational Regularization
A new algorithmic framework is proposed for learning autoencoders of data distributions.
Nested-Wasserstein Self-Imitation Learning for Sequence Generation
Reinforcement learning (RL) has been widely studied for improving sequence-generation models.
Toward Automatic Threat Recognition for Airport X-ray Baggage Screening with Deep Convolutional Object Detection
We show performance of our models on held-out evaluation sets, analyze several design parameters, and demonstrate the potential of such systems for automated detection of threats that can be found in airports.
On Fenchel Mini-Max Learning
Inference, estimation, sampling and likelihood evaluation are four primary goals of probabilistic modeling.
Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction
Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i. e., they remain adversarial even against other models.
Graph-Driven Generative Models for Heterogeneous Multi-Task Learning
We propose a novel graph-driven generative model, that unifies multiple heterogeneous learning tasks into the same framework.
Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding
Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks.
An End-to-End Generative Architecture for Paraphrase Generation
Generating high-quality paraphrases is a fundamental yet challenging natural language processing task.
Learning to Recommend from Sparse Data via Generative User Feedback
To address this, we propose a learning framework that improves collaborative filtering with a synthetic feedback loop (CF-SFL) to simulate the user feedback.
Zero-Shot Recognition via Optimal Transport
{Specifically, we build a conditional generative model to generate features from seen-class attributes, and establish an optimal transport between the distribution of the generated features and that of the real features.}
Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods
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
The Straight-Through (ST) estimator is a widely used technique for back-propagating gradients through discrete random variables.
Dynamic Embedding on Textual Networks via a Gaussian Process
The relative importance of global versus local structure for the embeddings is learned automatically.
Fused Gromov-Wasserstein Alignment for Hawkes Processes
Accordingly, the learned optimal transport reflects the correspondence between the event types of these two Hawkes processes.
Improving Textual Network Learning with Variational Homophilic Embeddings
This paper considers a novel variational formulation of network embeddings, with special focus on textual networks.
Ouroboros: On Accelerating Training of Transformer-Based Language Models
Model parallelism is required if a model is too large to fit in a single computing device.
Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation
Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains.
LMVP: Video Predictor with Leaked Motion Information
We propose a Leaked Motion Video Predictor (LMVP) to predict future frames by capturing the spatial and temporal dependencies from given inputs.
Adversarial Self-Paced Learning for Mixture Models of Hawkes Processes
Instead of learning a mixture model directly from a set of event sequences drawn from different Hawkes processes, the proposed method learns the target model iteratively, which generates "easy" sequences and uses them in an adversarial and self-paced manner.
Learning Compressed Sentence Representations for On-Device Text Processing
Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems.
Interpretable ICD Code Embeddings with Self- and Mutual-Attention Mechanisms
The proposed method achieves clinically-interpretable embeddings of ICD codes, and outperforms state-of-the-art embedding methods in procedure recommendation.
Towards Amortized Ranking-Critical Training for Collaborative Filtering
In this paper we investigate new methods for training collaborative filtering models based on actor-critic reinforcement learning, to directly optimize the non-differentiable quality metrics of interest.
Ranked #3 on
Recommendation Systems
on Million Song Dataset
Improving Textual Network Embedding with Global Attention via Optimal Transport
Constituting highly informative network embeddings is an important tool for network analysis.
Adaptation Across Extreme Variations using Unlabeled Domain Bridges
We tackle an unsupervised domain adaptation problem for which the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter and intra-domain variation.
Syntax-Infused Variational Autoencoder for Text Generation
We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences.
Topic-Guided Variational Auto-Encoder for Text Generation
We propose a topic-guided variational auto-encoder (TGVAE) model for text generation.
Survival Function Matching for Calibrated Time-to-Event Predictions
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.
Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching
Using this concept, we extend our method to multi-graph partitioning and matching by learning a Gromov-Wasserstein barycenter graph for multiple observed graphs; the barycenter graph plays the role of the disconnected graph, and since it is learned, so is the clustering.
On Norm-Agnostic Robustness of Adversarial Training
Adversarial examples are carefully perturbed in-puts for fooling machine learning models.
Stochastic Blockmodels meet Graph Neural Networks
Although we develop this framework for a particular type of SBM, namely the \emph{overlapping} stochastic blockmodel, the proposed framework can be adapted readily for other types of SBMs.
Second-Order Adversarial Attack and Certifiable Robustness
In this paper, we propose a powerful second-order attack method that reduces the accuracy of the defense model by Madry et al. (2017).
Weakly Supervised Instance Learning for Thyroid Malignancy Prediction from Whole Slide Cytopathology Images
The lower bound further allows us to extend the proposed algorithm to simultaneously predict multiple bag and instance-level labels from a single output of a neural network.
Thyroid Cancer Malignancy Prediction From Whole Slide Cytopathology Images
We consider preoperative prediction of thyroid cancer based on ultra-high-resolution whole-slide cytopathology images.
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks.
Topic-Guided Variational Autoencoders for Text Generation
We propose a topic-guided variational autoencoder (TGVAE) model for text generation.
Scalable Thompson Sampling via Optimal Transport
Thompson sampling (TS) is a class of algorithms for sequential decision-making, which requires maintaining a posterior distribution over a model.
Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation with latent variables.
Improving Sequence-to-Sequence Learning via Optimal Transport
Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE).
Gromov-Wasserstein Learning for Graph Matching and Node Embedding
A novel Gromov-Wasserstein learning framework is proposed to jointly match (align) graphs and learn embedding vectors for the associated graph nodes.
GO Gradient for Expectation-Based Objectives
Within many machine learning algorithms, a fundamental problem concerns efficient calculation of an unbiased gradient wrt parameters $\gammav$ for expectation-based objectives $\Ebb_{q_{\gammav} (\yv)} [f(\yv)]$.
Adversarial Learning of a Sampler Based on an Unnormalized Distribution
We investigate adversarial learning in the case when only an unnormalized form of the density can be accessed, rather than samples.
StoryGAN: A Sequential Conditional GAN for Story Visualization
We therefore propose a new story-to-image-sequence generation model, StoryGAN, based on the sequential conditional GAN framework.
Revisiting the Softmax Bellman Operator: New Benefits and New Perspective
The impact of softmax on the value function itself in reinforcement learning (RL) is often viewed as problematic because it leads to sub-optimal value (or Q) functions and interferes with the contraction properties of the Bellman operator.
Generative Adversarial Network Training is a Continual Learning Problem
We hypothesize that this is at least in part due to the evolution of the generator distribution and the catastrophic forgetting tendency of neural networks, which leads to the discriminator losing the ability to remember synthesized samples from previous instantiations of the generator.
Sequence Generation with Guider Network
Sequence generation with reinforcement learning (RL) has received significant attention recently.
Hierarchically-Structured Variational Autoencoders for Long Text Generation
Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation.
Adversarial Text Generation via Feature-Mover's Distance
However, the discrete nature of text hinders the application of GAN to text-generation tasks.
Distilled Wasserstein Learning for Word Embedding and Topic Modeling
When learning the topic model, we leverage a distilled underlying distance matrix to update the topic distributions and smoothly calculate the corresponding optimal transports.
Certified Adversarial Robustness with Additive Noise
The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning algorithm.
Predicting Smoking Events with a Time-Varying Semi-Parametric Hawkes Process Model
Health risks from cigarette smoking -- the leading cause of preventable death in the United States -- can be substantially reduced by quitting.
Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory
Particle-optimization-based sampling (POS) is a recently developed effective sampling technique that interactively updates a set of particles.
Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment
Network embeddings, which learn low-dimensional representations for each vertex in a large-scale network, have received considerable attention in recent years.
Policy Optimization as Wasserstein Gradient Flows
Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total reward, or its surrogate.
Understanding and Accelerating Particle-Based Variational Inference
Particle-based variational inference methods (ParVIs) have gained attention in the Bayesian inference literature, for their capacity to yield flexible and accurate approximations.
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains).
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring a substantial number of parameters and expensive computations.
Ranked #1 on
Named Entity Recognition (NER)
on CoNLL 2000
Diffusion Maps for Textual Network Embedding
Textual network embedding leverages rich text information associated with the network to learn low-dimensional vectorial representations of vertices.
NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing
Semantic hashing has become a powerful paradigm for fast similarity search in many information retrieval systems.
Joint Embedding of Words and Labels for Text Classification
Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences.
Ranked #11 on
Text Classification
on DBpedia
Adversarial Time-to-Event Modeling
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.
Nonlocal Low-Rank Tensor Factor Analysis for Image Restoration
Low-rank signal modeling has been widely leveraged to capture non-local correlation in image processing applications.
Superposition-Assisted Stochastic Optimization for Hawkes Processes
We consider the learning of multi-agent Hawkes processes, a model containing multiple Hawkes processes with shared endogenous impact functions and different exogenous intensities.
Multi-Label Learning from Medical Plain Text with Convolutional Residual Models
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.
On the Use of Word Embeddings Alone to Represent Natural Language Sequences
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.
Learning Structural Weight Uncertainty for Sequential Decision-Making
Learning probability distributions on the weights of neural networks (NNs) has recently proven beneficial in many applications.
Topic Compositional Neural Language Model
The TCNLM learns the global semantic coherence of a document via a neural topic model, and the probability of each learned latent topic is further used to build a Mixture-of-Experts (MoE) language model, where each expert (corresponding to one topic) is a recurrent neural network (RNN) that accounts for learning the local structure of a word sequence.
On Connecting Stochastic Gradient MCMC and Differential Privacy
Significant success has been realized recently on applying machine learning to real-world applications.
Cross-Spectral Factor Analysis
To facilitate understanding of network-level synchronization between brain regions, we introduce a novel model of multisite low-frequency neural recordings, such as local field potentials (LFPs) and electroencephalograms (EEGs).
Scalable Model Selection for Belief Networks
We propose a scalable algorithm for model selection in sigmoid belief networks (SBNs), based on the factorized asymptotic Bayesian (FAB) framework.
Targeting EEG/LFP Synchrony with Neural Nets
We consider the analysis of Electroencephalography (EEG) and Local Field Potential (LFP) datasets, which are “big” in terms of the size of recorded data but rarely have sufficient labels required to train complex models (e. g., conventional deep learning methods).
Zero-Shot Learning via Class-Conditioned Deep Generative Models
We present a deep generative model for learning to predict classes not seen at training time.
Adversarial Symmetric Variational Autoencoder
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.
Benefits from Superposed Hawkes Processes
The superposition of Hawkes processes is demonstrated to be beneficial for tightening the upper bound of excess risk under certain conditions, and we show the feasibility of the benefit in typical situations.
Learning Registered Point Processes from Idiosyncratic Observations
A parametric point process model is developed, with modeling based on the assumption that sequential observations often share latent phenomena, while also possessing idiosyncratic effects.
Learning Context-Sensitive Convolutional Filters for Text Processing
The role of meta network is to abstract the contextual information of a sentence or document into a set of input-aware filters.
Ranked #13 on
Text Classification
on DBpedia
Deconvolutional Latent-Variable Model for Text Sequence Matching
A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives.
Triangle Generative Adversarial Networks
The generators are designed to learn the two-way conditional distributions between the two domains, while the discriminators implicitly define a ternary discriminative function, which is trained to distinguish real data pairs and two kinds of fake data pairs.
Image-to-Image Translation
Semi-Supervised Image Classification
+1
A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks
We present a probabilistic framework for nonlinearities, based on doubly truncated Gaussian distributions.
An inner-loop free solution to inverse problems using deep neural networks
For matrix inversion in the second sub-problem, we learn a convolutional neural network to approximate the matrix inversion, i. e., the inverse mapping is learned by feeding the input through the learned forward network.
Symmetric Variational Autoencoder and Connections to Adversarial Learning
A new form of the variational autoencoder (VAE) is proposed, based on the symmetric Kullback-Leibler divergence.
ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching.
Continuous-Time Flows for Efficient Inference and Density Estimation
Distinct from normalizing flows and GANs, CTFs can be adopted to achieve the above two goals in one framework, with theoretical guarantees.
A Convergence Analysis for A Class of Practical Variance-Reduction Stochastic Gradient MCMC
However, there has been little theoretical analysis of the impact of minibatch size to the algorithm's convergence rate.
Deconvolutional Paragraph Representation Learning
Learning latent representations from long text sequences is an important first step in many natural language processing applications.
Deep Generative Models for Relational Data with Side Information
Moreover, inference cost scales in the number of edges which is attractive for massive but sparse networks.
Adversarial Feature Matching for Text Generation
We propose a framework for generating realistic text via adversarial training.
Stochastic Gradient Monomial Gamma Sampler
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
A new method for learning variational autoencoders (VAEs) is developed, based on Stein variational gradient descent.
Compressive Sensing via Convolutional Factor Analysis
During reconstruction and testing, we project the upper layer dictionary to the data level and only a single layer deconvolution is required.
Tensor-Dictionary Learning with Deep Kruskal-Factor Analysis
A multi-way factor analysis model is introduced for tensor-variate data of any order.
Linear Feature Encoding for Reinforcement Learning
We then develop a supervised linear feature encoding method that is motivated by insights from linear value function approximation theory, as well as empirical successes from deep RL.
Learning Generic Sentence Representations Using Convolutional Neural Networks
We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes.
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
Recurrent neural networks (RNNs) have shown promising performance for language modeling.
Semantic Compositional Networks for Visual Captioning
The degree to which each member of the ensemble is used to generate an image caption is tied to the image-dependent probability of the corresponding tag.
Adaptive Feature Abstraction for Translating Video to Text
Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features.
Unsupervised Learning with Truncated Gaussian Graphical Models
Gaussian graphical models (GGMs) are widely used for statistical modeling, because of ease of inference and the ubiquitous use of the normal distribution in practical approximations.