arXiv subjects

Jimeng Sun

Publications and source records attributed to Jimeng Sun.

At least 181 records · Page 10Linked to original sources

arXiv2020

ELF: An Early-Exiting Framework for Long-Tailed Classification

The natural world often follows a long-tailed data distribution where only a few classes account for most of the examples. This long-tail causes classifiers to overfit to the majority class. To mitigate this, prior solutions commonly adopt class rebalancing strategies such as data resampling and loss reshaping. However, by treating each example within a class equally, these methods fail to account for the important notion of example hardness, i.e., within each class some examples are easier to classify than others. To incorporate this notion of hardness into the learning process, we propose the EarLy-exiting Framework(ELF). During training, ELF learns to early-exit easy examples through auxiliary branches attached to a backbone network. This offers a dual benefit-(1) the neural network increasingly focuses on hard examples, since they contribute more to the overall network loss; and (2) it frees up additional model capacity to distinguish difficult examples. Experimental results on two large-scale datasets, ImageNet LT and iNaturalist'18, demonstrate that ELF can improve state-of-the-art accuracy by more than 3 percent. This comes with the additional benefit of reducing up to 20 percent of inference time FLOPS. ELF is complementary to prior work and can naturally integrate with a variety of existing methods to tackle the challenge of long-tailed distributions.

cs.LG↗

arXiv2020

SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates

Uncertainty quantification is a fundamental yet unsolved problem for deep learning. The Bayesian framework provides a principled way of uncertainty estimation but is often not scalable to modern deep neural nets (DNNs) that have a large number of parameters. Non-Bayesian methods are simple to implement but often conflate different sources of uncertainties and require huge computing resources. We propose a new method for quantifying uncertainties of DNNs from a dynamical system perspective. The core of our method is to view DNN transformations as state evolution of a stochastic dynamical system and introduce a Brownian motion term for capturing epistemic uncertainty. Based on this perspective, we propose a neural stochastic differential equation model (SDE-Net) which consists of (1) a drift net that controls the system to fit the predictive function; and (2) a diffusion net that captures epistemic uncertainty. We theoretically analyze the existence and uniqueness of the solution to SDE-Net. Our experiments demonstrate that the SDE-Net model can outperform existing uncertainty estimation methods across a series of tasks where uncertainty plays a fundamental role.

cs.LG↗

arXiv2020

HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units

Deep learning models have achieved expert-level performance in healthcare with an exclusive focus on training accurate models. However, in many clinical environments such as intensive care unit (ICU), real-time model serving is equally if not more important than accuracy, because in ICU patient care is simultaneously more urgent and more expensive. Clinical decisions and their timeliness, therefore, directly affect both the patient outcome and the cost of care. To make timely decisions, we argue the underlying serving system must be latency-aware. To compound the challenge, health analytic applications often require a combination of models instead of a single model, to better specialize individual models for different targets, multi-modal data, different prediction windows, and potentially personalized predictions. To address these challenges, we propose HOLMES-an online model ensemble serving framework for healthcare applications. HOLMES dynamically identifies the best performing set of models to ensemble for highest accuracy, while also satisfying sub-second latency constraints on end-to-end prediction. We demonstrate that HOLMES is able to navigate the accuracy/latency tradeoff efficiently, compose the ensemble, and serve the model ensemble pipeline, scaling to simultaneously streaming data from 100 patients, each producing waveform data at 250~Hz. HOLMES outperforms the conventional offline batch-processed inference for the same clinical task in terms of accuracy and latency (by order of magnitude). HOLMES is tested on risk prediction task on pediatric cardio ICU data with above 95% prediction accuracy and sub-second latency on 64-bed simulation.

cs.LG↗

arXiv2020

STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths

Taxonomies are important knowledge ontologies that underpin numerous applications on a daily basis, but many taxonomies used in practice suffer from the low coverage issue. We study the taxonomy expansion problem, which aims to expand existing taxonomies with new concept terms. We propose a self-supervised taxonomy expansion model named STEAM, which leverages natural supervision in the existing taxonomy for expansion. To generate natural self-supervision signals, STEAM samples mini-paths from the existing taxonomy, and formulates a node attachment prediction task between anchor mini-paths and query terms. To solve the node attachment task, it learns feature representations for query-anchor pairs from multiple views and performs multi-view co-training for prediction. Extensive experiments show that STEAM outperforms state-of-the-art methods for taxonomy expansion by 11.6\% in accuracy and 7.0\% in mean reciprocal rank on three public benchmarks. The implementation of STEAM can be found at \url{https://github.com/yueyu1030/STEAM}.

cs.CL↗

arXiv2020

COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching

Clinical trials play important roles in drug development but often suffer from expensive, inaccurate and insufficient patient recruitment. The availability of massive electronic health records (EHR) data and trial eligibility criteria (EC) bring a new opportunity to data driven patient recruitment. One key task named patient-trial matching is to find qualified patients for clinical trials given structured EHR and unstructured EC text (both inclusion and exclusion criteria). How to match complex EC text with longitudinal patient EHRs? How to embed many-to-many relationships between patients and trials? How to explicitly handle the difference between inclusion and exclusion criteria? In this paper, we proposed CrOss-Modal PseudO-SiamEse network (COMPOSE) to address these challenges for patient-trial matching. One path of the network encodes EC using convolutional highway network. The other path processes EHR with multi-granularity memory network that encodes structured patient records into multiple levels based on medical ontology. Using the EC embedding as query, COMPOSE performs attentional record alignment and thus enables dynamic patient-trial matching. COMPOSE also introduces a composite loss term to maximize the similarity between patient records and inclusion criteria while minimize the similarity to the exclusion criteria. Experiment results show COMPOSE can reach 98.0% AUC on patient-criteria matching and 83.7% accuracy on patient-trial matching, which leads 24.3% improvement over the best baseline on real-world patient-trial matching tasks.

cs.LG↗

arXiv2020

CHEER: Rich Model Helps Poor Model via Knowledge Infusion

There is a growing interest in applying deep learning (DL) to healthcare, driven by the availability of data with multiple feature channels in rich-data environments (e.g., intensive care units). However, in many other practical situations, we can only access data with much fewer feature channels in a poor-data environments (e.g., at home), which often results in predictive models with poor performance. How can we boost the performance of models learned from such poor-data environment by leveraging knowledge extracted from existing models trained using rich data in a related environment? To address this question, we develop a knowledge infusion framework named CHEER that can succinctly summarize such rich model into transferable representations, which can be incorporated into the poor model to improve its performance. The infused model is analyzed theoretically and evaluated empirically on several datasets. Our empirical results showed that CHEER outperformed baselines by 5.60% to 46.80% in terms of the macro-F1 score on multiple physiological datasets.

cs.LG↗

arXiv2020

Opportunities and Challenges of Deep Learning Methods for Electrocardiogram Data: A Systematic Review

Background:The electrocardiogram (ECG) is one of the most commonly used diagnostic tools in medicine and healthcare. Deep learning methods have achieved promising results on predictive healthcare tasks using ECG signals. Objective:This paper presents a systematic review of deep learning methods for ECG data from both modeling and application perspectives. Methods:We extracted papers that applied deep learning (deep neural network) models to ECG data that were published between Jan. 1st of 2010 and Feb. 29th of 2020 from Google Scholar, PubMed, and the DBLP. We then analyzed each article according to three factors: tasks, models, and data. Finally, we discuss open challenges and unsolved problems in this area. Results: The total number of papers extracted was 191. Among these papers, 108 were published after 2019. Different deep learning architectures have been used in various ECG analytics tasks, such as disease detection/classification, annotation/localization, sleep staging, biometric human identification, and denoising. Conclusion: The number of works on deep learning for ECG data has grown explosively in recent years. Such works have achieved accuracy comparable to that of traditional feature-based approaches and ensembles of multiple approaches can achieve even better results. Specifically, we found that a hybrid architecture of a convolutional neural network and recurrent neural network ensemble using expert features yields the best results. However, there are some new challenges and problems related to interpretability, scalability, and efficiency that must be addressed. Furthermore, it is also worth investigating new applications from the perspectives of datasets and methods. Significance: This paper summarizes existing deep learning research using ECG data from multiple perspectives and highlights existing challenges and problems to identify potential future research directions.

eess.SP↗

arXiv2020

MolTrans: Molecular Interaction Transformer for Drug Target Interaction Prediction

Drug target interaction (DTI) prediction is a foundational task for in silico drug discovery, which is costly and time-consuming due to the need of experimental search over large drug compound space. Recent years have witnessed promising progress for deep learning in DTI predictions. However, the following challenges are still open: (1) the sole data-driven molecular representation learning approaches ignore the sub-structural nature of DTI, thus produce results that are less accurate and difficult to explain; (2) existing methods focus on limited labeled data while ignoring the value of massive unlabelled molecular data. We propose a Molecular Interaction Transformer (MolTrans) to address these limitations via: (1) knowledge inspired sub-structural pattern mining algorithm and interaction modeling module for more accurate and interpretable DTI prediction; (2) an augmented transformer encoder to better extract and capture the semantic relations among substructures extracted from massive unlabeled biomedical data. We evaluate MolTrans on real world data and show it improved DTI prediction performance compared to state-of-the-art baselines.

q-bio.QM↗

arXiv2020

CLARA: Clinical Report Auto-completion

Generating clinical reports from raw recordings such as X-rays and electroencephalogram (EEG) is an essential and routine task for doctors. However, it is often time-consuming to write accurate and detailed reports. Most existing methods try to generate the whole reports from the raw input with limited success because 1) generated reports often contain errors that need manual review and correction, 2) it does not save time when doctors want to write additional information into the report, and 3) the generated reports are not customized based on individual doctors' preference. We propose {\it CL}inic{\it A}l {\it R}eport {\it A}uto-completion (CLARA), an interactive method that generates reports in a sentence by sentence fashion based on doctors' anchor words and partially completed sentences. CLARA searches for most relevant sentences from existing reports as the template for the current report. The retrieved sentences are sequentially modified by combining with the input feature representations to create the final report. In our experimental evaluation, CLARA achieved 0.393 CIDEr and 0.248 BLEU-4 on X-ray reports and 0.482 CIDEr and 0.491 BLEU-4 for EEG reports for sentence-level generation, which is up to 35% improvement over the best baseline. Also via our qualitative evaluation, CLARA is shown to produce reports which have a significantly higher level of approval by doctors in a user study (3.74 out of 5 for CLARA vs 2.52 out of 5 for the baseline).

cs.LG↗

arXiv2020

REST: Robust and Efficient Neural Networks for Sleep Monitoring in the Wild

In recent years, significant attention has been devoted towards integrating deep learning technologies in the healthcare domain. However, to safely and practically deploy deep learning models for home health monitoring, two significant challenges must be addressed: the models should be (1) robust against noise; and (2) compact and energy-efficient. We propose REST, a new method that simultaneously tackles both issues via 1) adversarial training and controlling the Lipschitz constant of the neural network through spectral regularization while 2) enabling neural network compression through sparsity regularization. We demonstrate that REST produces highly-robust and efficient models that substantially outperform the original full-sized models in the presence of noise. For the sleep staging task over single-channel electroencephalogram (EEG), the REST model achieves a macro-F1 score of 0.67 vs. 0.39 achieved by a state-of-the-art model in the presence of Gaussian noise while obtaining 19x parameter reduction and 15x MFLOPS reduction on two large, real-world EEG datasets. By deploying these models to an Android application on a smartphone, we quantitatively observe that REST allows models to achieve up to 17x energy reduction and 9x faster inference. We open-source the code repository with this paper: https://github.com/duggalrahul/REST.

eess.SP↗

arXiv2020

StageNet: Stage-Aware Neural Networks for Health Risk Prediction

Deep learning has demonstrated success in health risk prediction especially for patients with chronic and progressing conditions. Most existing works focus on learning disease Network (StageNet) model to extract disease stage information from patient data and integrate it into risk prediction. StageNet is enabled by (1) a stage-aware long short-term memory (LSTM) module that extracts health stage variations unsupervisedly; (2) a stage-adaptive convolutional module that incorporates stage-related progression patterns into risk prediction. We evaluate StageNet on two real-world datasets and show that StageNet outperforms state-of-the-art models in risk prediction task and patient subtyping task. Compared to the best baseline model, StageNet achieves up to 12% higher AUPRC for risk prediction task on two real-world patient datasets. StageNet also achieves over 58% higher Calinski-Harabasz score (a cluster quality metric) for a patient subtyping task.

cs.LG↗

arXiv2020

DeepEnroll: Patient-Trial Matching with Deep Embedding and Entailment Prediction

Clinical trials are essential for drug development but often suffer from expensive, inaccurate and insufficient patient recruitment. The core problem of patient-trial matching is to find qualified patients for a trial, where patient information is stored in electronic health records (EHR) while trial eligibility criteria (EC) are described in text documents available on the web. How to represent longitudinal patient EHR? How to extract complex logical rules from EC? Most existing works rely on manual rule-based extraction, which is time consuming and inflexible for complex inference. To address these challenges, we proposed DeepEnroll, a cross-modal inference learning model to jointly encode enrollment criteria (text) and patients records (tabular data) into a shared latent space for matching inference. DeepEnroll applies a pre-trained Bidirectional Encoder Representations from Transformers(BERT) model to encode clinical trial information into sentence embedding. And uses a hierarchical embedding model to represent patient longitudinal EHR. In addition, DeepEnroll is augmented by a numerical information embedding and entailment module to reason over numerical information in both EC and EHR. These encoders are trained jointly to optimize patient-trial matching score. We evaluated DeepEnroll on the trial-patient matching task with demonstrated on real world datasets. DeepEnroll outperformed the best baseline by up to 12.4% in average F1.

cs.AI↗

arXiv2019

Guaranteed Scalable Learning of Latent Tree Models

We present an integrated approach for structure and parameter estimation in latent tree graphical models. Our overall approach follows a "divide-and-conquer" strategy that learns models over small groups of variables and iteratively merges onto a global solution. The structure learning involves combinatorial operations such as minimum spanning tree construction and local recursive grouping; the parameter learning is based on the method of moments and on tensor decompositions. Our method is guaranteed to correctly recover the unknown tree structure and the model parameters with low sample complexity for the class of linear multivariate latent tree models which includes discrete and Gaussian distributions, and Gaussian mixtures. Our bulk asynchronous parallel algorithm is implemented in parallel and the parallel computation complexity increases only logarithmically with the number of variables and linearly with dimensionality of each variable.

cs.LG↗

arXiv2019

Pre-training of Graph Augmented Transformers for Medication Recommendation

Medication recommendation is an important healthcare application. It is commonly formulated as a temporal prediction task. Hence, most existing works only utilize longitudinal electronic health records (EHRs) from a small number of patients with multiple visits ignoring a large number of patients with a single visit (selection bias). Moreover, important hierarchical knowledge such as diagnosis hierarchy is not leveraged in the representation learning process. To address these challenges, we propose G-BERT, a new model to combine the power of Graph Neural Networks (GNNs) and BERT (Bidirectional Encoder Representations from Transformers) for medical code representation and medication recommendation. We use GNNs to represent the internal hierarchical structures of medical codes. Then we integrate the GNN representation into a transformer-based visit encoder and pre-train it on EHR data from patients only with a single visit. The pre-trained visit encoder and representation are then fine-tuned for downstream predictive tasks on longitudinal EHRs from patients with multiple visits. G-BERT is the first to bring the language model pre-training schema into the healthcare domain and it achieved state-of-the-art performance on the medication recommendation task.

cs.AI↗

arXiv2019

CONAN: Complementary Pattern Augmentation for Rare Disease Detection

Rare diseases affect hundreds of millions of people worldwide but are hard to detect since they have extremely low prevalence rates (varying from 1/1,000 to 1/200,000 patients) and are massively underdiagnosed. How do we reliably detect rare diseases with such low prevalence rates? How to further leverage patients with possibly uncertain diagnosis to improve detection? In this paper, we propose a Complementary pattern Augmentation (CONAN) framework for rare disease detection. CONAN combines ideas from both adversarial training and max-margin classification. It first learns self-attentive and hierarchical embedding for patient pattern characterization. Then, we develop a complementary generative adversarial networks (GAN) model to generate candidate positive and negative samples from the uncertain patients by encouraging a max-margin between classes. In addition, CONAN has a disease detector that serves as the discriminator during the adversarial training for identifying rare diseases. We evaluated CONAN on two disease detection tasks. For low prevalence inflammatory bowel disease (IBD) detection, CONAN achieved .96 precision recall area under the curve (PR-AUC) and 50.1% relative improvement over best baseline. For rare disease idiopathic pulmonary fibrosis (IPF) detection, CONAN achieves .22 PR-AUC with 41.3% relative improvement over the best baseline.

cs.LG↗

arXiv2019

Doctor2Vec: Dynamic Doctor Representation Learning for Clinical Trial Recruitment

Massive electronic health records (EHRs) enable the success of learning accurate patient representations to support various predictive health applications. In contrast, doctor representation was not well studied despite that doctors play pivotal roles in healthcare. How to construct the right doctor representations? How to use doctor representation to solve important health analytic problems? In this work, we study the problem on {\it clinical trial recruitment}, which is about identifying the right doctors to help conduct the trials based on the trial description and patient EHR data of those doctors. We propose doctor2vec which simultaneously learns 1) doctor representations from EHR data and 2) trial representations from the description and categorical information about the trials. In particular, doctor2vec utilizes a dynamic memory network where the doctor's experience with patients are stored in the memory bank and the network will dynamically assign weights based on the trial representation via an attention mechanism. Validated on large real-world trials and EHR data including 2,609 trials, 25K doctors and 430K patients, doctor2vec demonstrated improved performance over the best baseline by up to $8.7\%$ in PR-AUC. We also demonstrated that the doctor2vec embedding can be transferred to benefit data insufficiency settings including trial recruitment in less populated/newly explored country with $13.7\%$ improvement or for rare diseases with $8.1\%$ improvement in PR-AUC.

cs.LG↗

arXiv2019

CORE: Automatic Molecule Optimization Using Copy & Refine Strategy

Molecule optimization is about generating molecule $Y$ with more desirable properties based on an input molecule $X$. The state-of-the-art approaches partition the molecules into a large set of substructures $S$ and grow the new molecule structure by iteratively predicting which substructure from $S$ to add. However, since the set of available substructures $S$ is large, such an iterative prediction task is often inaccurate especially for substructures that are infrequent in the training data. To address this challenge, we propose a new generating strategy called "Copy & Refine" (CORE), where at each step the generator first decides whether to copy an existing substructure from input $X$ or to generate a new substructure, then the most promising substructure will be added to the new molecule. Combining together with scaffolding tree generation and adversarial training, CORE can significantly improve several latest molecule optimization methods in various measures including drug likeness (QED), dopamine receptor (DRD2) and penalized LogP. We tested CORE and baselines using the ZINC database and CORE obtained up to 11% and 21% relatively improvement over the baselines on success rate on the complete test set and the subset with infrequent substructures, respectively.

cs.LG↗

arXiv2019

CASTER: Predicting Drug Interactions with Chemical Substructure Representation

Adverse drug-drug interactions (DDIs) remain a leading cause of morbidity and mortality. Identifying potential DDIs during the drug design process is critical for patients and society. Although several computational models have been proposed for DDI prediction, there are still limitations: (1) specialized design of drug representation for DDI predictions is lacking; (2) predictions are based on limited labelled data and do not generalize well to unseen drugs or DDIs; and (3) models are characterized by a large number of parameters, thus are hard to interpret. In this work, we develop a ChemicAl SubstrucTurE Representation (CASTER) framework that predicts DDIs given chemical structures of drugs.CASTER aims to mitigate these limitations via (1) a sequential pattern mining module rooted in the DDI mechanism to efficiently characterize functional sub-structures of drugs; (2) an auto-encoding module that leverages both labelled and unlabelled chemical structure data to improve predictive accuracy and generalizability; and (3) a dictionary learning module that explains the prediction via a small set of coefficients which measure the relevance of each input sub-structures to the DDI outcome. We evaluated CASTER on two real-world DDI datasets and showed that it performed better than state-of-the-art baselines and provided interpretable predictions.

cs.LG↗