Search Results for author: Pengyu Hong

Found 28 papers, 8 papers with code

Multiple Abstraction Level Retrieve Augment Generation

no code implementations28 Jan 2025 Zheng Zheng, Xinyi Ni, Pengyu Hong

A Retrieval-Augmented Generation (RAG) model powered by a large language model (LLM) provides a faster and more cost-effective solution for adapting to new data and knowledge.

Language Modeling Language Modelling +3

ToolFactory: Automating Tool Generation by Leveraging LLM to Understand REST API Documentations

no code implementations28 Jan 2025 Xinyi Ni, Qiuyang Wang, Yukun Zhang, Pengyu Hong

ToolFactory exhibits significant potential for facilitating the seamless integration of scientific REST APIs into AI workflows.

AI Agent

Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

1 code implementation20 Nov 2024 Yoel Zimmermann, Adib Bazgir, Zartashia Afzal, Fariha Agbere, Qianxiang Ai, Nawaf Alampara, Alexander Al-Feghali, Mehrad Ansari, Dmytro Antypov, Amro Aswad, Jiaru Bai, Viktoriia Baibakova, Devi Dutta Biswajeet, Erik Bitzek, Joshua D. Bocarsly, Anna Borisova, Andres M Bran, L. Catherine Brinson, Marcel Moran Calderon, Alessandro Canalicchio, Victor Chen, Yuan Chiang, Defne Circi, Benjamin Charmes, Vikrant Chaudhary, Zizhang Chen, Min-Hsueh Chiu, Judith Clymo, Kedar Dabhadkar, Nathan Daelman, Archit Datar, Wibe A. de Jong, Matthew L. Evans, Maryam Ghazizade Fard, Giuseppe Fisicaro, Abhijeet Sadashiv Gangan, Janine George, Jose D. Cojal Gonzalez, Michael Götte, Ankur K. Gupta, Hassan Harb, Pengyu Hong, Abdelrahman Ibrahim, Ahmed Ilyas, Alishba Imran, Kevin Ishimwe, Ramsey Issa, Kevin Maik Jablonka, Colin Jones, Tyler R. Josephson, Greg Juhasz, Sarthak Kapoor, Rongda Kang, Ghazal Khalighinejad, Sartaaj Khan, Sascha Klawohn, Suneel Kuman, Alvin Noe Ladines, Sarom Leang, Magdalena Lederbauer, Sheng-Lun, Liao, Hao liu, Xuefeng Liu, Stanley Lo, Sandeep Madireddy, Piyush Ranjan Maharana, Shagun Maheshwari, Soroush Mahjoubi, José A. Márquez, Rob Mills, Trupti Mohanty, Bernadette Mohr, Seyed Mohamad Moosavi, Alexander Moßhammer, Amirhossein D. Naghdi, Aakash Naik, Oleksandr Narykov, Hampus Näsström, Xuan Vu Nguyen, Xinyi Ni, Dana O'Connor, Teslim Olayiwola, Federico Ottomano, Aleyna Beste Ozhan, Sebastian Pagel, Chiku Parida, Jaehee Park, Vraj Patel, Elena Patyukova, Martin Hoffmann Petersen, Luis Pinto, José M. Pizarro, Dieter Plessers, Tapashree Pradhan, Utkarsh Pratiush, Charishma Puli, Andrew Qin, Mahyar Rajabi, Francesco Ricci, Elliot Risch, Martiño Ríos-García, Aritra Roy, Tehseen Rug, Hasan M Sayeed, Markus Scheidgen, Mara Schilling-Wilhelmi, Marcel Schloz, Fabian Schöppach, Julia Schumann, Philippe Schwaller, Marcus Schwarting, Samiha Sharlin, Kevin Shen, Jiale Shi, Pradip Si, Jennifer D'Souza, Taylor Sparks, Suraj Sudhakar, Leopold Talirz, Dandan Tang, Olga Taran, Carla Terboven, Mark Tropin, Anastasiia Tsymbal, Katharina Ueltzen, Pablo Andres Unzueta, Archit Vasan, Tirtha Vinchurkar, Trung Vo, Gabriel Vogel, Christoph Völker, Jan Weinreich, Faradawn Yang, Mohd Zaki, Chi Zhang, Sylvester Zhang, Weijie Zhang, Ruijie Zhu, Shang Zhu, Jan Janssen, Calvin Li, Ian Foster, Ben Blaiszik

Here, we present the outcomes from the second Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry, which engaged participants across global hybrid locations, resulting in 34 team submissions.

Language Modeling Language Modelling +2

Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack

no code implementations18 Nov 2024 Nicole Meng, Caleb Manicke, David Chen, Yingjie Lao, Caiwen Ding, Pengyu Hong, Kaleel Mahmood

For generating adversarial examples, decision based black-box attacks are one of the most practical techniques as they only require query access to the model.

reinforcement-learning Reinforcement Learning

TransPeakNet: Solvent-Aware 2D NMR Prediction via Multi-Task Pre-Training and Unsupervised Learning

1 code implementation17 Mar 2024 Yunrui Li, Hao Xu, Ambrish Kumar, Duosheng Wang, Christian Heiss, Parastoo Azadi, Pengyu Hong

Nuclear Magnetic Resonance (NMR) spectroscopy is essential for revealing molecular structure, electronic environment, and dynamics.

Graph Multi-Similarity Learning for Molecular Property Prediction

no code implementations31 Jan 2024 Hao Xu, Zhengyang Zhou, Pengyu Hong

Additionally, previous multi-similarity approaches require the specification of positive and negative pairs to attribute distinct predefined weights to different relative similarities, which can introduce potential bias.

Attribute Contrastive Learning +6

GlycoNMR: Dataset and benchmarks for NMR chemical shift prediction of carbohydrates with graph neural networks

no code implementations28 Nov 2023 Zizhang Chen, Ryan Paul Badman, Lachele Foley, Robert Woods, Pengyu Hong

This under-exploration can be primarily attributed to the limited availability of comprehensive and well-curated carbohydrate-specific datasets and a lack of Machine learning (ML) pipelines specifically tailored to meet the unique problems presented by carbohydrate data.

Drug Design molecular representation +2

Enhancing Peak Assignment in 13C NMR Spectroscopy: A Novel Approach Using Multimodal Alignment

no code implementations23 Nov 2023 Hao Xu, Zhengyang Zhou, Pengyu Hong

Nuclear magnetic resonance (NMR) spectroscopy plays an essential role in deciphering molecular structure and dynamic behaviors.

Contrastive Learning Meta-Learning +1

Asymmetric Contrastive Multimodal Learning for Advancing Chemical Understanding

1 code implementation11 Nov 2023 Hao Xu, Yifei Wang, Yunrui Li, Lin Liu, Pengyu Hong

ACML harnesses the power of effective asymmetric contrastive learning to seamlessly transfer information from various chemical modalities to molecular graph representations.

Contrastive Learning Drug Discovery +4

Counterpart Fairness -- Addressing Systematic between-group Differences in Fairness Evaluation

1 code implementation29 May 2023 Yifei Wang, Zhengyang Zhou, Liqin Wang, John Laurentiev, Peter Hou, Li Zhou, Pengyu Hong

When using machine learning to aid decision-making, it is critical to ensure that an algorithmic decision is fair and does not discriminate against specific individuals/groups, particularly those from underprivileged populations.

Decision Making Fairness +1

Characterizing the Influence of Graph Elements

no code implementations14 Oct 2022 Zizhang Chen, Peizhao Li, Hongfu Liu, Pengyu Hong

To fill this gap, we started with the simple graph convolution (SGC) model that operates on an attributed graph and formulated an influence function to approximate the changes in model parameters when a node or an edge is removed from an attributed graph.

Motif-based Graph Representation Learning with Application to Chemical Molecules

1 code implementation9 Aug 2022 Yifei Wang, Shiyang Chen, Guobin Chen, Ethan Shurberg, Hang Liu, Pengyu Hong

MCM builds a motif vocabulary in an unsupervised way and deploys a novel motif convolution operation to extract the local structural context of individual nodes, which is then used to learn higher-level node representations via multilayer perceptron and/or message passing in graph neural networks.

Graph Learning Graph Representation Learning

Knowledgebra: An Algebraic Learning Framework for Knowledge Graph

no code implementations15 Apr 2022 Tong Yang, Yifei Wang, Long Sha, Jan Engelbrecht, Pengyu Hong

As far as we know, by applying abstract algebra in statistical learning, this work develops the first formal language for general knowledge graphs, and also sheds light on the problem of neural-symbolic integration from an algebraic perspective.

Abstract Algebra General Knowledge +3

Graph-Graph Similarity Network

no code implementations1 Jan 2021 Han Yue, Pengyu Hong, Hongfu Liu

In this paper, we propose a Graph-Graph Similarity Network to tackle the graph classification problem by constructing a SuperGraph through learning the relationships among graphs.

General Classification Graph Classification +2

Variance Regularization for Accelerating Stochastic Optimization

no code implementations13 Aug 2020 Tong Yang, Long Sha, Pengyu Hong

While nowadays most gradient-based optimization methods focus on exploring the high-dimensional geometric features, the random error accumulated in a stochastic version of any algorithm implementation has not been stressed yet.

Stochastic Optimization

A Deep Learning Approach for COVID-19 Trend Prediction

no code implementations9 Aug 2020 Tong Yang, Long Sha, Justin Li, Pengyu Hong

In this work, we developed a deep learning model-based approach to forecast the spreading trend of SARS-CoV-2 in the United States.

Deep Learning Time Series +1

NagE: Non-Abelian Group Embedding for Knowledge Graphs

no code implementations22 May 2020 Tong Yang, Long Sha, Pengyu Hong

We demonstrated the existence of a group algebraic structure hidden in relational knowledge embedding problems, which suggests that a group-based embedding framework is essential for designing embedding models.

Knowledge Graph Embedding Knowledge Graphs

Probabilistic Connection Importance Inference and Lossless Compression of Deep Neural Networks

no code implementations ICLR 2020 Xin Xing, Long Sha, Pengyu Hong, Zuofeng Shang, Jun S. Liu

Deep neural networks (DNNs) can be huge in size, requiring a considerable a mount of energy and computational resources to operate, which limits their applications in numerous scenarios.

A Group-Theoretic Framework for Knowledge Graph Embedding

no code implementations25 Sep 2019 Tong Yang, Long Sha, Pengyu Hong

We have rigorously proved the existence of a group algebraic structure hidden in relational knowledge embedding problems, which suggests that a group-based embedding framework is essential for model design.

Knowledge Graph Embedding

Detecting Topological Defects in 2D Active Nematics Using Convolutional Neural Networks

no code implementations ICLR 2019 Ruoshi Liu, Michael M. Norton, Seth Fraden, Pengyu Hong

Active matter consists of active agents which transform energy extracted from surroundings into momentum, producing a variety of collective phenomena.

Defect Detection

Context Dependent Modulation of Activation Function

no code implementations ICLR 2019 Long Sha, Jonathan Schwarcz, Pengyu Hong

This modification produces statistically significant improvements in comparison with traditional ANN nodes in the context of Convolutional Neural Networks and Long Short-Term Memory networks.

Robust Detection of Adversarial Attacks by Modeling the Intrinsic Properties of Deep Neural Networks

no code implementations NeurIPS 2018 Zhi-Hao Zheng, Pengyu Hong

Our approach tries to capture the intrinsic properties of a DNN classifier and uses them to detect adversarial inputs.

Cannot find the paper you are looking for? You can Submit a new open access paper.