Samuel Kim

Michael Zhang, Samuel Kim, Peter Y. Lu et al. · mit

Symbolic regression is a machine learning technique that can learn the governing formulas of data and thus has the potential to transform scientific discovery. However, symbolic regression is still limited in the complexity and dimensionality of the systems that it can analyze. Deep learning on the other hand has transformed machine learning in its ability to analyze extremely complex and high-dimensional datasets. We propose a neural network architecture to extend symbolic regression to parametric systems where some coefficient may vary but the structure of the underlying governing equation remains constant. We demonstrate our method on various analytic expressions, ODEs, and PDEs with varying coefficients and show that it extrapolates well outside of the training domain. The neural network-based architecture can also integrate with other deep learning architectures so that it can analyze high-dimensional data while being trained end-to-end. To this end we integrate our architecture with convolutional neural networks to analyze 1D images of varying spring systems.

Won Joon Yun, Samuel Kim, Joongheon Kim

The prodigious growth of digital health data has precipitated a mounting interest in harnessing machine learning methodologies, such as natural language processing (NLP), to scrutinize medical records, clinical notes, and other text-based health information. Although NLP techniques have exhibited substantial potential in augmenting patient care and informing clinical decision-making, data privacy and adherence to regulations persist as critical concerns. Federated learning (FL) emerges as a viable solution, empowering multiple organizations to train machine learning models collaboratively without disseminating raw data. This paper proffers a pragmatic approach to medical NLP by amalgamating FL, NLP models, and the NVFlare framework, developed by NVIDIA. We introduce two exemplary NLP models, the Long-Short Term Memory (LSTM)-based model and Bidirectional Encoder Representations from Transformers (BERT), which have demonstrated exceptional performance in comprehending context and semantics within medical data. This paper encompasses the development of an integrated framework that addresses data privacy and regulatory compliance challenges while maintaining elevated accuracy and performance, incorporating BERT pretraining, and comprehensively substantiating the efficacy of the proposed approach.

Viggo Moro, Charlotte Loh, Rumen Dangovski et al.

Artificial intelligence is transforming computational materials science, improving the prediction of material properties, and accelerating the discovery of novel materials. Recently, publicly available material data repositories have grown rapidly. This growth encompasses not only more materials but also a greater variety and quantity of their associated properties. Existing machine learning efforts in materials science focus primarily on single-modality tasks, i.e. relationships between materials and a single physical property, thus not taking advantage of the rich and multimodal set of material properties. Here, we introduce Multimodal Learning for Materials (MultiMat), which enables self-supervised multi-modality training of foundation models for materials. We demonstrate our framework's potential using data from the Materials Project database on multiple axes: (i) MultiMat achieves state-of-the-art performance for challenging material property prediction tasks; (ii) MultiMat enables novel and accurate material discovery via latent space similarity, enabling screening for stable materials with desired properties; and (iii) MultiMat encodes interpretable emergent features that may provide novel scientific insights.

Soojin Lee, Ingu Sean Lee, Samuel Kim

Chronic Obstructive Pulmonary Disease (COPD) is an irreversible airway obstruction with a high societal burden. Although smoking is known to be the biggest risk factor, additional components need to be considered. In this study, we aim to identify COPD risk factors by applying machine learning models that integrate sociodemographic, clinical, and genetic data to predict COPD development.

Willie Kang, Sean Kim, Eliot Yoo et al.

While acute stress has been shown to have both positive and negative effects on performance, not much is known about the impacts of stress on students grades during examinations. To answer this question, we examined whether a correlation could be found between physiological stress signals and exam performance. We conducted this study using multiple physiological signals of ten undergraduate students over three different exams. The study focused on three signals, i.e., skin temperature, heart rate, and electrodermal activity. We extracted statistics as features and fed them into a variety of binary classifiers to predict relatively higher or lower grades. Experimental results showed up to 0.81 ROC-AUC with k-nearest neighbor algorithm among various machine learning algorithms.

Sean Kim, Eliot Yoo, Samuel Kim

Graduation and dropout rates have always been a serious consideration for educational institutions and students. High dropout rates negatively impact both the lives of individual students and institutions. To address this problem, this study examined university dropout prediction using academic, demographic, socioeconomic, and macroeconomic data types. Additionally, we performed associated factor analysis to analyze which type of data would be most influential on the performance of machine learning models in predicting graduation and dropout status. These features were used to train four binary classifiers to determine if students would graduate or drop out. The overall performance of the classifiers in predicting dropout status had an average ROC-AUC score of 0.935. The data type most influential to the model performance was found to be academic data, with the average ROC-AUC score dropping from 0.935 to 0.811 when excluding all academic-related features from the data set. Preliminary results indicate that a correlation does exist between data types and dropout status.

Samuel Kim, In Gu Sean Lee, Mijeong Irene Ban et al.

We propose machine learning algorithms to automatically detect and predict clopidogrel treatment failure using longitudinal structured electronic health records (EHR). By drawing analogies between natural language and structured EHR, we introduce various machine learning algorithms used in natural language processing (NLP) applications to build models for treatment failure detection and prediction. In this regard, we generated a cohort of patients with clopidogrel prescriptions from UK Biobank and annotated if the patients had treatment failure events within one year of the first clopidogrel prescription; out of 502,527 patients, 1,824 patients were identified as treatment failure cases, and 6,859 patients were considered as control cases. From the dataset, we gathered diagnoses, prescriptions, and procedure records together per patient and organized them into visits with the same date to build models. The models were built for two different tasks, i.e., detection and prediction, and the experimental results showed that time series models outperform bag-of-words approaches in both tasks. In particular, a Transformer-based model, namely BERT, could reach 0.928 AUC in detection tasks and 0.729 AUC in prediction tasks. BERT also showed competence over other time series models when there is not enough training data, because it leverages the pre-training procedure using large unlabeled data.

Sean Kim, Samuel Kim

Mental disorders impact the lives of millions of people globally, not only impeding their day-to-day lives but also markedly reducing life expectancy. This paper addresses the persistent challenge of predicting mortality in patients with mental diagnoses using predictive machine-learning models with electronic health records (EHR). Data from patients with mental disease diagnoses were extracted from the well-known clinical MIMIC-III data set utilizing demographic, prescription, and procedural information. Four machine learning algorithms (Logistic Regression, Random Forest, Support Vector Machine, and K-Nearest Neighbors) were used, with results indicating that Random Forest and Support Vector Machine models outperformed others, with AUC scores of 0.911. Feature importance analysis revealed that drug prescriptions, particularly Morphine Sulfate, play a pivotal role in prediction. We applied a variety of machine learning algorithms to predict 30-day mortality followed by feature importance analysis. This study can be used to assist hospital workers in identifying at-risk patients to reduce excess mortality.

Bach Pham, JuiHsuan Wong, Samuel Kim et al.

Dictionary definitions are historically the arbitrator of what words mean, but this primacy has come under threat by recent progress in NLP, including word embeddings and generative models like ChatGPT. We present an exploratory study of the degree of alignment between word definitions from classical dictionaries and these newer computational artifacts. Specifically, we compare definitions from three published dictionaries to those generated from variants of ChatGPT. We show that (i) definitions from different traditional dictionaries exhibit more surface form similarity than do model-generated definitions, (ii) that the ChatGPT definitions are highly accurate, comparable to traditional dictionaries, and (iii) ChatGPT-based embedding definitions retain their accuracy even on low frequency words, much better than GloVE and FastText word embeddings.

Sunwoong Choi, Samuel Kim

We present a novel data augmentation method to address the challenge of data scarcity in modeling longitudinal patterns in Electronic Health Records (EHR) of patients using natural language processing (NLP) algorithms. The proposed method generates augmented data by rearranging the orders of medical records within a visit where the order of elements are not obvious, if any. Applying the proposed method to the clopidogrel treatment failure detection task enabled up to 5.3% absolute improvement in terms of ROC-AUC (from 0.908 without augmentation to 0.961 with augmentation) when it was used during the pre-training procedure. It was also shown that the augmentation helped to improve performance during fine-tuning procedures, especially when the amount of labeled training data is limited.

Samuel Kim, Min Sang Kim

The effectiveness of clopidogrel, a widely used antiplatelet medication, varies significantly among individuals, necessitating the development of precise predictive models to optimize patient care. In this study, we leverage federated learning strategies to address clopidogrel treatment failure detection. Our research harnesses the collaborative power of multiple healthcare institutions, allowing them to jointly train machine learning models while safeguarding sensitive patient data. Utilizing the UK Biobank dataset, which encompasses a vast and diverse population, we partitioned the data based on geographic centers and evaluated the performance of federated learning. Our results show that while centralized training achieves higher Area Under the Curve (AUC) values and faster convergence, federated learning approaches can substantially narrow this performance gap. Our findings underscore the potential of federated learning in addressing clopidogrel treatment failure detection, offering a promising avenue for enhancing patient care through personalized treatment strategies while respecting data privacy. This study contributes to the growing body of research on federated learning in healthcare and lays the groundwork for secure and privacy-preserving predictive models for various medical conditions.

Charlotte Loh, Thomas Christensen, Rumen Dangovski et al.

Deep learning techniques have been increasingly applied to the natural sciences, e.g., for property prediction and optimization or material discovery. A fundamental ingredient of such approaches is the vast quantity of labelled data needed to train the model; this poses severe challenges in data-scarce settings where obtaining labels requires substantial computational or labor resources. Here, we introduce surrogate- and invariance-boosted contrastive learning (SIB-CL), a deep learning framework which incorporates three ``inexpensive'' and easily obtainable auxiliary information sources to overcome data scarcity. Specifically, these are: 1)~abundant unlabeled data, 2)~prior knowledge of symmetries or invariances and 3)~surrogate data obtained at near-zero cost. We demonstrate SIB-CL's effectiveness and generality on various scientific problems, e.g., predicting the density-of-states of 2D photonic crystals and solving the 3D time-independent Schrodinger equation. SIB-CL consistently results in orders of magnitude reduction in the number of labels needed to achieve the same network accuracies.

Samuel Kim, Peter Y. Lu, Charlotte Loh et al.

Bayesian optimization (BO) is a popular paradigm for global optimization of expensive black-box functions, but there are many domains where the function is not completely a black-box. The data may have some known structure (e.g. symmetries) and/or the data generation process may be a composite process that yields useful intermediate or auxiliary information in addition to the value of the optimization objective. However, surrogate models traditionally employed in BO, such as Gaussian Processes (GPs), scale poorly with dataset size and do not easily accommodate known structure. Instead, we use Bayesian neural networks, a class of scalable and flexible surrogate models with inductive biases, to extend BO to complex, structured problems with high dimensionality. We demonstrate BO on a number of realistic problems in physics and chemistry, including topology optimization of photonic crystal materials using convolutional neural networks, and chemical property optimization of molecules using graph neural networks. On these complex tasks, we show that neural networks often outperform GPs as surrogate models for BO in terms of both sampling efficiency and computational cost.

Owen Dugan, Rumen Dangovski, Allan Costa et al.

Neural networks' expressiveness comes at the cost of complex, black-box models that often extrapolate poorly beyond the domain of the training dataset, conflicting with the goal of finding compact analytic expressions to describe scientific data. We introduce OccamNet, a neural network model that finds interpretable, compact, and sparse symbolic fits to data, à la Occam's razor. Our model defines a probability distribution over functions with efficient sampling and function evaluation. We train by sampling functions and biasing the probability mass toward better fitting solutions, backpropagating using cross-entropy matching in a reinforcement-learning loss. OccamNet can identify symbolic fits for a variety of problems, including analytic and non-analytic functions, implicit functions, and simple image classification, and can outperform state-of-the-art symbolic regression methods on real-world regression datasets. Our method requires a minimal memory footprint, fits complicated functions in minutes on a single CPU, and scales on a GPU.

Samuel Kim, Peter Y. Lu, Srijon Mukherjee et al.

Symbolic regression is a powerful technique that can discover analytical equations that describe data, which can lead to explainable models and generalizability outside of the training data set. In contrast, neural networks have achieved amazing levels of accuracy on image recognition and natural language processing tasks, but are often seen as black-box models that are difficult to interpret and typically extrapolate poorly. Here we use a neural network-based architecture for symbolic regression called the Equation Learner (EQL) network and integrate it with other deep learning architectures such that the whole system can be trained end-to-end through backpropagation. To demonstrate the power of such systems, we study their performance on several substantially different tasks. First, we show that the neural network can perform symbolic regression and learn the form of several functions. Next, we present an MNIST arithmetic task where a separate part of the neural network extracts the digits. Finally, we demonstrate prediction of dynamical systems where an unknown parameter is extracted through an encoder. We find that the EQL-based architecture can extrapolate quite well outside of the training data set compared to a standard neural network-based architecture, paving the way for deep learning to be applied in scientific exploration and discovery.

Samuel Kim, Namhee Kwon, Henry O'Connell

Estimating personal well-being draws increasing attention particularly from healthcare and pharmaceutical industries. We propose an approach to estimate personal well-being in terms of various measurements such as anxiety, sleep quality and mood using voice. With clinically validated questionnaires to score those measurements in a self-assessed way, we extract salient features from voice and train regression models with deep neural networks. Experiments with the collected database of 219 subjects show promising results in predicting the well-being related measurements; concordance correlation coefficients (CCC) between self-assessed scores and predicted scores are 0.41 for anxiety, 0.44 for sleep quality and 0.38 for mood.

Peter Y. Lu, Samuel Kim, Marin Soljačić

Experimental data is often affected by uncontrolled variables that make analysis and interpretation difficult. For spatiotemporal systems, this problem is further exacerbated by their intricate dynamics. Modern machine learning methods are particularly well-suited for analyzing and modeling complex datasets, but to be effective in science, the result needs to be interpretable. We demonstrate an unsupervised learning technique for extracting interpretable physical parameters from noisy spatiotemporal data and for building a transferable model of the system. In particular, we implement a physics-informed architecture based on variational autoencoders that is designed for analyzing systems governed by partial differential equations (PDEs). The architecture is trained end-to-end and extracts latent parameters that parameterize the dynamics of a learned predictive model for the system. To test our method, we train our model on simulated data from a variety of PDEs with varying dynamical parameters that act as uncontrolled variables. Numerical experiments show that our method can accurately identify relevant parameters and extract them from raw and even noisy spatiotemporal data (tested with roughly 10% added noise). These extracted parameters correlate well (linearly with $R^2 > 0.95$) with the ground truth physical parameters used to generate the datasets. We then apply this method to nonlinear fiber propagation data, generated by an ab-initio simulation, to demonstrate its capabilities on a more realistic dataset. Our method for discovering interpretable latent parameters in spatiotemporal systems will allow us to better analyze and understand real-world phenomena and datasets, which often have unknown and uncontrolled variables that alter the system dynamics and cause varying behaviors that are difficult to disentangle.