arXiv subjects

Bowen Deng

Publications and source records attributed to Bowen Deng.

48 records · Page 3Linked to original sources

arXiv2024

Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning

Machine learning interatomic potentials (MLIPs) have introduced a new paradigm for atomic simulations. Recent advancements have seen the emergence of universal MLIPs (uMLIPs) that are pre-trained on diverse materials datasets, providing opportunities for both ready-to-use universal force fields and robust foundations for downstream machine learning refinements. However, their performance in extrapolating to out-of-distribution complex atomic environments remains unclear. In this study, we highlight a consistent potential energy surface (PES) softening effect in three uMLIPs: M3GNet, CHGNet, and MACE-MP-0, which is characterized by energy and force under-prediction in a series of atomic-modeling benchmarks including surfaces, defects, solid-solution energetics, phonon vibration modes, ion migration barriers, and general high-energy states. We find that the PES softening behavior originates from a systematic underprediction error of the PES curvature, which derives from the biased sampling of near-equilibrium atomic arrangements in uMLIP pre-training datasets. We demonstrate that the PES softening issue can be effectively rectified by fine-tuning with a single additional data point. Our findings suggest that a considerable fraction of uMLIP errors are highly systematic, and can therefore be efficiently corrected. This result rationalizes the data-efficient fine-tuning performance boost commonly observed with foundational MLIPs. We argue for the importance of a comprehensive materials dataset with improved PES sampling for next-generation foundational MLIPs.

cond-mat.mtrl-sci↗

arXiv2024

Deep learning of experimental electrochemistry for battery cathodes across diverse compositions

Artificial intelligence (AI) has emerged as a tool for discovering and optimizing novel battery materials. However, the adoption of AI in battery cathode representation and discovery is still limited due to the complexity of optimizing multiple performance properties and the scarcity of high-fidelity data. In this study, we present a machine-learning model (DRXNet) for battery informatics and demonstrate the application in the discovery and optimization of disordered rocksalt (DRX) cathode materials. We have compiled the electrochemistry data of DRX cathodes over the past five years, resulting in a dataset of more than 19,000 discharge voltage profiles on diverse chemistries spanning 14 different metal species. Learning from this extensive dataset, our DRXNet model can automatically capture critical features in the cycling curves of DRX cathodes under various conditions. Illustratively, the model gives rational predictions of the discharge capacity for diverse compositions in the Li--Mn--O--F chemical space as well as for high-entropy systems. As a universal model trained on diverse chemistries, our approach offers a data-driven solution to facilitate the rapid identification of novel cathode materials, accelerating the development of next-generation batteries for carbon neutralization.

cond-mat.mtrl-sci↗

arXiv2024

TadML: A fast temporal action detection with Mechanics-MLP

Temporal Action Detection(TAD) is a crucial but challenging task in video understanding.It is aimed at detecting both the type and start-end frame for each action instance in a long, untrimmed video.Most current models adopt both RGB and Optical-Flow streams for the TAD task. Thus, original RGB frames must be converted manually into Optical-Flow frames with additional computation and time cost, which is an obstacle to achieve real-time processing. At present, many models adopt two-stage strategies, which would slow the inference speed down and complicatedly tuning on proposals generating.By comparison, we propose a one-stage anchor-free temporal localization method with RGB stream only, in which a novel Newtonian Mechanics-MLP architecture is established. It has comparable accuracy with all existing state-of-the-art models, while surpasses the inference speed of these methods by a large margin. The typical inference speed in this paper is astounding 4.44 video per second on THUMOS14. In applications, because there is no need to convert optical flow, the inference speed will be faster.It also proves that MLP has great potential in downstream tasks such as TAD. The source code is available at https://github.com/BonedDeng/TadML

cs.CV↗

arXiv2023

CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling

The simulation of large-scale systems with complex electron interactions remains one of the greatest challenges for the atomistic modeling of materials. Although classical force fields often fail to describe the coupling between electronic states and ionic rearrangements, the more accurate \textit{ab-initio} molecular dynamics suffers from computational complexity that prevents long-time and large-scale simulations, which are essential to study many technologically relevant phenomena, such as reactions, ion migrations, phase transformations, and degradation. In this work, we present the Crystal Hamiltonian Graph neural Network (CHGNet) as a novel machine-learning interatomic potential (MLIP), using a graph-neural-network-based force field to model a universal potential energy surface. CHGNet is pretrained on the energies, forces, stresses, and magnetic moments from the Materials Project Trajectory Dataset, which consists of over 10 years of density functional theory static and relaxation trajectories of $\sim 1.5$ million inorganic structures. The explicit inclusion of magnetic moments enables CHGNet to learn and accurately represent the orbital occupancy of electrons, enhancing its capability to describe both atomic and electronic degrees of freedom. We demonstrate several applications of CHGNet in solid-state materials, including charge-informed molecular dynamics in Li$_x$MnO$_2$, the finite temperature phase diagram for Li$_x$FePO$_4$ and Li diffusion in garnet conductors. We critically analyze the significance of including charge information for capturing appropriate chemistry, and we provide new insights into ionic systems with additional electronic degrees of freedom that can not be observed by previous MLIPs.

cond-mat.mtrl-sci↗

arXiv2023

Catalysis distillation neural network for the few shot open catalyst challenge

The integration of artificial intelligence and science has resulted in substantial progress in computational chemistry methods for the design and discovery of novel catalysts. Nonetheless, the challenges of electrocatalytic reactions and developing a large-scale language model in catalysis persist, and the recent success of ChatGPT's (Chat Generative Pre-trained Transformer) few-shot methods surpassing BERT (Bidirectional Encoder Representation from Transformers) underscores the importance of addressing limited data, expensive computations, time constraints and structure-activity relationship in research. Hence, the development of few-shot techniques for catalysis is critical and essential, regardless of present and future requirements. This paper introduces the Few-Shot Open Catalyst Challenge 2023, a competition aimed at advancing the application of machine learning technology for predicting catalytic reactions on catalytic surfaces, with a specific focus on dual-atom catalysts in hydrogen peroxide electrocatalysis. To address the challenge of limited data in catalysis, we propose a machine learning approach based on MLP-Like and a framework called Catalysis Distillation Graph Neural Network (CDGNN). Our results demonstrate that CDGNN effectively learns embeddings from catalytic structures, enabling the capture of structure-adsorption relationships. This accomplishment has resulted in the utmost advanced and efficient determination of the reaction pathway for hydrogen peroxide, surpassing the current graph neural network approach by 16.1%.. Consequently, CDGNN presents a promising approach for few-shot learning in catalysis.

physics.chem-ph↗

arXiv2022

Graph Analysis in Decentralized Online Social Networks with Fine-Grained Privacy Protection

Graph analysts cannot directly obtain the global structure in decentralized social networks, and analyzing such a network requires collecting local views of the social graph from individual users. Since the edges between users may reveal sensitive social interactions in the local view, applying differential privacy in the data collection process is often desirable, which provides strong and rigorous privacy guarantees. In practical decentralized social graphs, different edges have different privacy requirements due to the distinct sensitivity levels. However, the existing differentially private analysis of social graphs provide the same protection for all edges. To address this issue, this work proposes a fine-grained privacy notion as well as novel algorithms for private graph analysis. We first design a fine-grained relationship differential privacy (FGR-DP) notion for social graph analysis, which enforces different protections for the edges with distinct privacy requirements. Then, we design algorithms for triangle counting and k-stars counting, respectively, which can accurately estimate subgraph counts given fine-grained protection for social edges. We also analyze upper bounds on the estimation error, including k-stars and triangle counts, and show their superior performance compared with the state-of-the-arts. Finally, we perform extensive experiments on two real social graph datasets and demonstrate that the proposed mechanisms satisfying FGR-DP have better utility than the state-of-the-art mechanisms due to the finer-grained protection.

cs.CR↗

arXiv2022

ULSA: Unified Language of Synthesis Actions for Representation of Synthesis Protocols

Applying AI power to predict syntheses of novel materials requires high-quality, large-scale datasets. Extraction of synthesis information from scientific publications is still challenging, especially for extracting synthesis actions, because of the lack of a comprehensive labeled dataset using a solid, robust, and well-established ontology for describing synthesis procedures. In this work, we propose the first Unified Language of Synthesis Actions (ULSA) for describing ceramics synthesis procedures. We created a dataset of 3,040 synthesis procedures annotated by domain experts according to the proposed ULSA scheme. To demonstrate the capabilities of ULSA, we built a neural network-based model to map arbitrary ceramics synthesis paragraphs into ULSA and used it to construct synthesis flowcharts for synthesis procedures. Analysis for the flowcharts showed that (a) ULSA covers essential vocabulary used by researchers when describing synthesis procedures and (b) it can capture important features of synthesis protocols. This work is an important step towards creating a synthesis ontology and a solid foundation for autonomous robotic synthesis.

cs.LG↗

arXiv2021

Addressing Multiple Salient Object Detection via Dual-Space Long-Range Dependencies

Salient object detection plays an important role in many downstream tasks. However, complex real-world scenes with varying scales and numbers of salient objects still pose a challenge. In this paper, we directly address the problem of detecting multiple salient objects across complex scenes. We propose a network architecture incorporating non-local feature information in both the spatial and channel spaces, capturing the long-range dependencies between separate objects. Traditional bottom-up and non-local features are combined with edge features within a feature fusion gate that progressively refines the salient object prediction in the decoder. We show that our approach accurately locates multiple salient regions even in complex scenarios. To demonstrate the efficacy of our approach to the multiple salient objects problem, we curate a new dataset containing only multiple salient objects. Our experiments demonstrate the proposed method presents state-of-the-art results on five widely used datasets without any pre-processing and post-processing. We obtain a further performance improvement against competing techniques on our multi-objects dataset. The dataset and source code are avaliable at: https://github.com/EricDengbowen/DSLRDNet.

cs.CV↗

arXiv2020

Phonon softening near topological phase transitions

Topological phase transitions occur when the electronic bands change their topological properties, typically featuring the closing of the bandgap. While the influence of topological phase transitions on electronic and optical properties has been extensively studied, its implication on phononic properties and thermal transport remains unexplored. In this work, we use first-principles simulations to show that certain phonon modes are significantly softened near topological phase transitions, leading to increased phonon-phonon scattering and reduced lattice thermal conductivity. We demonstrate this effect using two model systems: pressure-induced topological phase transition in $\rm ZrTe_5$ and chemical composition induced topological phase transition in $\rm{Hg_{1-x}Cd_{x}Te}$. We attribute the phonon softening to emergent Kohn anomalies associated with the closing of the bandgap. Our study reveals the strong connection between electronic band structures and lattice instabilities and opens up a potential direction towards controlling heat conduction in solids.

cond-mat.mtrl-sci↗

arXiv2019

Layer Dependence of Stacking Order in Nonencapsulated Few-layer CrI3

Long-range magnetic orders in atomically thin ferromagnetic CrI3 give rise to new fascinating physics and application perspectives. The physical properties of two-dimensional (2D) ferromagnetism CrI3 are significantly influenced by interlayer spacing and stacking order, which are sensitive to the hydrostatic pressure and external environments. However, there remains debate on the stacking order at low temperature. Here, we study the interlayer coupling and stacking order of non-encapsulated 2-5 layer and bulk CrI3 at 10 K by Raman spectroscopy; demonstrate a rhombohedral stacking in both antiferromagnetic and ferromagnetic CrI3. The opposite helicity dependence of Ag and Eg modes arising from phonon symmetry further validate the rhombohedral stacking. An anomalous temperature-dependent behavior is observed due to spin-phonon coupling below 60 K. Our work provides insights into the interlayer coupling and stacking orders of 2D ferromagnetic materials.

cond-mat.mtrl-sci↗

arXiv2019

Soft phonons and ultralow lattice thermal conductivity in the Dirac semimetal Cd3As2

Recently, Cd3As2 has attracted intensive research interest as an archetypical Dirac semimetal, hosting three-dimensional linear-dispersive electronic bands near the Fermi level. Previous studies have shown that single-crystalline Cd3As2 has an anomalously low lattice thermal conductivity, ranging from 0.3 W/mK to 0.7 W/mK at 300 K, which has been attributed to point defects. In this work, we combine first-principles lattice dynamics calculations and temperature-dependent high-resolution Raman spectroscopy of high-quality single-crystal thin films grown by molecular beam epitaxy to reveal the existence of a group of soft optical phonon modes at the Brillouin zone center of Cd3As2. These soft phonon modes significantly increase the scattering phase space of heat-carrying acoustic phonons and are the origin of the low lattice thermal conductivity of Cd3As2. Furthermore, we show that the interplay between the phonon-phonon Umklapp scattering rates and the soft optical phonon frequency explains the unusual non-monotonic temperature dependence of the lattice thermal conductivity of Cd3As2. Our results further suggest that the soft phonon modes are potentially induced by a Kohn anomaly associated with the Dirac nodes, in analogy to similar, nonetheless weaker, effects in graphene and Weyl semimetals.

cond-mat.mtrl-sci↗

arXiv2018

Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow

For tasks like code synthesis from natural language, code retrieval, and code summarization, data-driven models have shown great promise. However, creating these models require parallel data between natural language (NL) and code with fine-grained alignments. Stack Overflow (SO) is a promising source to create such a data set: the questions are diverse and most of them have corresponding answers with high-quality code snippets. However, existing heuristic methods (e.g., pairing the title of a post with the code in the accepted answer) are limited both in their coverage and the correctness of the NL-code pairs obtained. In this paper, we propose a novel method to mine high-quality aligned data from SO using two sets of features: hand-crafted features considering the structure of the extracted snippets, and correspondence features obtained by training a probabilistic model to capture the correlation between NL and code using neural networks. These features are fed into a classifier that determines the quality of mined NL-code pairs. Experiments using Python and Java as test beds show that the proposed method greatly expands coverage and accuracy over existing mining methods, even when using only a small number of labeled examples. Further, we find that reasonable results are achieved even when training the classifier on one language and testing on another, showing promise for scaling NL-code mining to a wide variety of programming languages beyond those for which we are able to annotate data.

cs.CL↗