arXiv subjects

Kenneth Chiu

Publications and source records attributed to Kenneth Chiu.

11 recordsLinked to original sources

arXiv2025

Score-based Idempotent Distillation of Diffusion Models

Idempotent generative networks (IGNs) are a new line of generative models based on idempotent mapping to a target manifold. IGNs support both single-and multi-step generation, allowing for a flexible trade-off between computational cost and sample quality. But similar to Generative Adversarial Networks (GANs), conventional IGNs require adversarial training and are prone to training instabilities and mode collapse. Diffusion and score-based models are popular approaches to generative modeling that iteratively transport samples from one distribution, usually a Gaussian, to a target data distribution. These models have gained popularity due to their stable training dynamics and high-fidelity generation quality. However, this stability and quality come at the cost of high computational cost, as the data must be transported incrementally along the entire trajectory. New sampling methods, model distillation, and consistency models have been developed to reduce the sampling cost and even perform one-shot sampling from diffusion models. In this work, we unite diffusion and IGNs by distilling idempotent models from diffusion model scores, called SIGN. Our proposed method is highly stable and does not require adversarial losses. We provide a theoretical analysis of our proposed score-based training methods and empirically show that IGNs can be effectively distilled from a pre-trained diffusion model, enabling faster inference than iterative score-based models. SIGNs can perform multi-step sampling, allowing users to trade off quality for efficiency. These models operate directly on the source domain; they can project corrupted or alternate distributions back onto the target manifold, enabling zero-shot editing of inputs. We validate our models on multiple image datasets, achieving state-of-the-art results for idempotent models on the CIFAR and CelebA datasets.

cs.LG↗

arXiv2025

BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models

Data-driven molecular discovery leverages artificial intelligence/machine learning (AI/ML) and generative modeling to filter and design novel molecules. Discovering novel molecules requires accurate out-of-distribution (OOD) predictions, but ML models struggle to generalize OOD. Currently, no systematic benchmarks exist for molecular OOD prediction tasks. We present $\mathbf{BOOM}$, $\mathbf{b}$enchmarks for $\mathbf{o}$ut-$\mathbf{o}$f-distribution $\mathbf{m}$olecular property predictions: a chemically-informed benchmark for OOD performance on common molecular property prediction tasks. We evaluate over 150 model-task combinations to benchmark deep learning models on OOD performance. Overall, we find that no existing model achieves strong generalization across all tasks: even the top-performing model exhibited an average OOD error 3x higher than in-distribution. Current chemical foundation models do not show strong OOD extrapolation, while models with high inductive bias can perform well on OOD tasks with simple, specific properties. We perform extensive ablation experiments, highlighting how data generation, pre-training, hyperparameter optimization, model architecture, and molecular representation impact OOD performance. Developing models with strong OOD generalization is a new frontier challenge in chemical ML. This open-source benchmark is available at https://github.com/FLASK-LLNL/BOOM

cs.LG↗

arXiv2024

PtychoFormer: A Transformer-based Model for Ptychographic Phase Retrieval

Ptychography is a computational method of microscopy that recovers high-resolution transmission images of samples from a series of diffraction patterns. While conventional phase retrieval algorithms can iteratively recover the images, they require oversampled diffraction patterns, incur significant computational costs, and struggle to recover the absolute phase of the sample's transmission function. Deep learning algorithms for ptychography are a promising approach to resolving the limitations of iterative algorithms. We present PtychoFormer, a hierarchical transformer-based model for data-driven single-shot ptychographic phase retrieval. PtychoFormer processes subsets of diffraction patterns, generating local inferences that are seamlessly stitched together to produce a high-quality reconstruction. Our model exhibits tolerance to sparsely scanned diffraction patterns and achieves up to 3600 times faster imaging speed than the extended ptychographic iterative engine (ePIE). We also propose the extended-PtychoFormer (ePF), a hybrid approach that combines the benefits of PtychoFormer with the ePIE. ePF minimizes global phase shifts and significantly enhances reconstruction quality, achieving state-of-the-art phase retrieval in ptychography.

eess.IV↗

arXiv2023

Distributed Reinforcement Learning for Molecular Design: Antioxidant case

Deep reinforcement learning has successfully been applied for molecular discovery as shown by the Molecule Deep Q-network (MolDQN) algorithm. This algorithm has challenges when applied to optimizing new molecules: training such a model is limited in terms of scalability to larger datasets and the trained model cannot be generalized to different molecules in the same dataset. In this paper, a distributed reinforcement learning algorithm for antioxidants, called DA-MolDQN is proposed to address these problems. State-of-the-art bond dissociation energy (BDE) and ionization potential (IP) predictors are integrated into DA-MolDQN, which are critical chemical properties while optimizing antioxidants. Training time is reduced by algorithmic improvements for molecular modifications. The algorithm is distributed, scalable for up to 512 molecules, and generalizes the model to a diverse set of molecules. The proposed models are trained with a proprietary antioxidant dataset. The results have been reproduced with both proprietary and public datasets. The proposed molecules have been validated with DFT simulations and a subset of them confirmed in public "unseen" datasets. In summary, DA-MolDQN is up to 100x faster than previous algorithms and can discover new optimized molecules from proprietary and public antioxidants.

cs.LG↗

arXiv2023

STRIDE: Structure-guided Generation for Inverse Design of Molecules

Machine learning and especially deep learning has had an increasing impact on molecule and materials design. In particular, given the growing access to an abundance of high-quality small molecule data for generative modeling for drug design, results for drug discovery have been promising. However, for many important classes of materials such as catalysts, antioxidants, and metal-organic frameworks, such large datasets are not available. Such families of molecules with limited samples and structural similarities are especially prevalent for industrial applications. As is well-known, retraining and even fine-tuning are challenging on such small datasets. Novel, practically applicable molecules are most often derivatives of well-known molecules, suggesting approaches to addressing data scarcity. To address this problem, we introduce $\textbf{STRIDE}$, a generative molecule workflow that generates novel molecules with an unconditional generative model guided by known molecules without any retraining. We generate molecules outside of the training data from a highly specialized set of antioxidant molecules. Our generated molecules have on average 21.7% lower synthetic accessibility scores and also reduce ionization potential by 5.9% of generated molecules via guiding.

physics.chem-ph↗

arXiv2022

ParticleGrid: Enabling Deep Learning using 3D Representation of Materials

From AlexNet to Inception, autoencoders to diffusion models, the development of novel and powerful deep learning models and learning algorithms has proceeded at breakneck speeds. In part, we believe that rapid iteration of model architecture and learning techniques by a large community of researchers over a common representation of the underlying entities has resulted in transferable deep learning knowledge. As a result, model scale, accuracy, fidelity, and compute performance have dramatically increased in computer vision and natural language processing. On the other hand, the lack of a common representation for chemical structure has hampered similar progress. To enable transferable deep learning, we identify the need for a robust 3-dimensional representation of materials such as molecules and crystals. The goal is to enable both materials property prediction and materials generation with 3D structures. While computationally costly, such representations can model a large set of chemical structures. We propose $\textit{ParticleGrid}$, a SIMD-optimized library for 3D structures, that is designed for deep learning applications and to seamlessly integrate with deep learning frameworks. Our highly optimized grid generation allows for generating grids on the fly on the CPU, reducing storage and GPU compute and memory requirements. We show the efficacy of 3D grids generated via $\textit{ParticleGrid}$ and accurately predict molecular energy properties using a 3D convolutional neural network. Our model is able to get 0.006 mean square error and nearly match the values calculated using computationally costly density functional theory at a fraction of the time.

cs.CE↗

arXiv2021

Epistasis Detection Via the Joint Cumulant

Selecting influential nonlinear interactive features from ultrahigh dimensional data has been an important task in various fields. However, statistical accuracy and computational feasibility are the two biggest concerns when more than half a million features are collected in practice. Many extant feature screening approaches are either focused on only main effects or heavily rely on heredity structure, hence rendering them ineffective in a scenario presenting strong interactive but weak main effects. In this article, we propose a new interaction screening procedure based on joint cumulant (named JCI-SIS). We show that the proposed procedure has strong sure screening consistency and is theoretically sound to support its performance. Simulation studies designed for both continuous and categorical predictors are performed to demonstrate the versatility and practicability of our JCI-SIS method. We further illustrate the power of JCI-SIS by applying it to screen 27,554,602,881 interaction pairs involving 234,754 single nucleotide polymorphisms (SNPs) for each of the 4,000 subjects collected from polycystic ovary syndrome (PCOS) patients and healthy controls.

stat.ME↗

arXiv2020

Graph Neural Network for Metal Organic Framework Potential Energy Approximation

Metal-organic frameworks (MOFs) are nanoporous compounds composed of metal ions and organic linkers. MOFs play an important role in industrial applications such as gas separation, gas purification, and electrolytic catalysis. Important MOF properties such as potential energy are currently computed via techniques such as density functional theory (DFT). Although DFT provides accurate results, it is computationally costly. We propose a machine learning approach for estimating the potential energy of candidate MOFs, decomposing it into separate pair-wise atomic interactions using a graph neural network. Such a technique will allow high-throughput screening of candidates MOFs. We also generate a database of 50,000 spatial configurations and high-quality potential energy values using DFT.

cs.LG↗

arXiv2019

Formal Foundations of Continuous Graph Processing

With the growing need for online and iterative graph processing, software systems that continuously process large-scale graphs become widely deployed. With optimizations inherent as part of their design, these systems are complex, and have unique features beyond conventional graph processing. This paper describes CG Calculus, the first semantic foundation for continuous graph processing. The calculus captures the essential behavior of both the backend graph processing engine and the frontend application, with a focus on two essential features: temporal locality optimization (TLO) and incremental operation processing (IOP). A key design insight is that the operations continuously applied to the graph can be captured by a semantics defined over the operation stream flowing through the graph nodes. CG Calculus is a systematic study on the correctness of building continuous graph processing systems and applications. The most important result is result determinism: despite significant non-deterministic executions introduced by TLO and IOP, the results produced by CG Calculus are the same as conventional graph processing without TLO or IOP. The metatheory of CG Calculus is mechanized in Coq.

cs.PL↗

arXiv2019

Towards Run Time Estimation of the Gaussian Chemistry Code for SEAGrid Science Gateway

Accurate estimation of the run time of computational codes has a number of significant advantages for scientific computing. It is required information for optimal resource allocation, improving turnaround times and utilization of science gateways. Furthermore, it allows users to better plan and schedule their research, streamlining workflows and improving the overall productivity of cyberinfrastructure. Predicting run time is challenging, however. The inputs to scientific codes can be complex and high dimensional. Their relationship to the run time may be highly non-linear, and, in the most general case is completely arbitrary and thus unpredictable (i.e., simply a random mapping from inputs to run time). Most codes are not so arbitrary, however, and there has been significant prior research on predicting the run time of applications and workloads. Such predictions are generally application-specific, however. In this paper, we focus on the Gaussian computational chemistry code. We characterize a data set of runs from the SEAGrid science gateway with a number of different studies. We also explore a number of different potential regression methods and present promising future directions.

physics.comp-ph↗

arXiv2005

A File System Abstraction for Sense and Respond Systems

The heterogeneity and resource constraints of sense-and-respond systems pose significant challenges to system and application development. In this paper, we present a flexible, intuitive file system abstraction for organizing and managing sense-and-respond systems based on the Plan 9 design principles. A key feature of this abstraction is the ability to support multiple views of the system via filesystem namespaces. Constructed logical views present an application-specific representation of the network, thus enabling high-level programming of the network. Concurrently, structural views of the network enable resource-efficient planning and execution of tasks. We present and motivate the design using several examples, outline research challenges and our research plan to address them, and describe the current state of implementation.

cs.NI↗