检索结果-内蒙古大学图书馆

Expressivity and Generalization: Fragment-Biases for Molecular GNNs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wollschläger, Tom Kemper, Niklas Hetzel, Leon Sommer, Johanna Günnemann, Stephan School of Computation Information & Technology Technical University of Munich Germany Munich Data Science Institute Germany Helmholtz Center for Computational Health Munich Germany

Although recent advances in higher-order Graph Neural Networks (GNNs) improve the theoretical expressiveness and molecular property predictive performance, they often fall short of the empirical performance of models that explicitly use fragment information as inductive bias. However, for these approaches, there exists no theoretic expressivity study. In this work, we propose the Fragment-WL test, an extension to the well-known Weisfeiler & Leman (WL) test, which enables the theoretic analysis of these fragment-biased GNNs. Building on the insights gained from the Fragment-WL test, we develop a new GNN architecture and a fragmentation with infinite vocabulary that significantly boosts expressiveness. We show the effectiveness of our model on synthetic and real-world data where we outperform all GNNs on Peptides and have 12% lower error than all GNNs on ZINC and 34% lower error than other fragment-biased models. Furthermore, we show that our model exhibits superior generalization capabilities compared to the latest transformer-based architectures, positioning it as a robust solution for a range of molecular modeling tasks. © 2024, CC BY.

关键词： Graph neural networks

Language Model Evolutionary Algorithms for Recommender Systems: Benchmarks and Algorithm Comparisons

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Jiao Sun, Zhu Feng, Shanshan Chen, Caishun Ong, Yew-Soon College of Computing & Data Science Nanyang Technological University Singapore Information Systems Technology and Design Singapore University of Technology and Design Singapore Centre for Frontier AI Research A*STAR The Institute of High Performance Computing A*STAR Singapore

In the evolutionary computing community, the remarkable language-handling capabilities and reasoning power of large language models (LLMs) have significantly enhanced the functionality of evolutionary algorithms (EAs), enabling them to tackle optimization problems involving structured language or program code. Although this field is still in its early stages, its impressive potential has led to the development of various LLM-based EAs. To effectively evaluate the performance and practical applicability of these LLM-based EAs, benchmarks with real-world relevance are essential. In this paper, we focus on LLM-based recommender systems (RSs) and introduce a benchmark problem set, named RSBench, specifically designed to assess the performance of LLM-based EAs in recommendation prompt optimization. RSBench emphasizes session-based recommendations, aiming to discover a set of Pareto optimal prompts that guide the recommendation process, providing accurate, diverse, and fair recommendations. We develop three LLM-based EAs based on established EA frameworks and experimentally evaluate their performance using RSBench. Our study offers valuable insights into the application of EAs in LLM-based RSs. Additionally, we explore key components that may influence the overall performance of the RS, providing meaningful guidance for future research on the development of LLM-based EAs in RSs. © 2024, CC BY.

关键词： Algorithmic languages

A Distribution Optimization Framework for Confidence Bounds of Risk Measures

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liang, Hao Luo, Zhi-Quan School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data China

We present a distribution optimization framework that significantly improves confidence bounds for various risk measures compared to previous methods. Our framework encompasses popular risk measures such as the entropic risk measure, conditional value at risk (CVaR), spectral risk measure, distortion risk measure, equivalent certainty, and rank-dependent expected utility, which are well established in risk-sensitive decision-making literature. To achieve this, we introduce two estimation schemes based on concentration bounds derived from the empirical distribution, specifically using either the Wasserstein distance or the supremum distance. Unlike traditional approaches that add or subtract a confidence radius from the empirical risk measures, our proposed schemes evaluate a specific transformation of the empirical distribution based on the distance. Consequently, our confidence bounds consistently yield tighter results compared to previous methods. We further verify the efficacy of the proposed framework by providing tighter problem-dependent regret bound for the CVaR bandit. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

Wastewater-based epidemiology to monitor 68 NPS/conventional drug use in Taipei metropolitan area in Taiwan during and after COVID-19 pandemic

学校读者我要写书评

暂无评论

Journal of Hazardous Materials 2024年 476卷 135020页

作者： Ting, Te-Tien Chen, Pin-Chuan Chang, Ya-Chi Chiang, Pin-Ju Li, Hsu-Cheng Chen, Shih-Hsun Chen, Pei-Chieh Chu, Hai-Tien Chuang, Ping-Yu Liu, Yi-Hsin Chen, Pai-Shan Department of Data Science School of Big Data Management Soochow University Taipei Taiwan Department of Mechanical Engineering National Taiwan University of Science and Technology Taipei Taiwan Graduate Institute of Toxicology National Taiwan University College of Medicine National Taiwan University Taipei Taiwan Department of Chemistry National Taiwan Normal University Taipei Taiwan

Amidst far-reaching COVID-19 effects and social constraints, this study leveraged wastewater-based epidemiology to track 38 conventional drugs and 30 new psychoactive substances (NPS) in northern Taiwan. Analyzing daily samples from four Taipei wastewater plants between September 2021 and January 2024—encompassing club reopenings, holidays, Lunar New Year, an outbreak, and regular periods—thirty-one drugs were detected, including 5 NPS. Tramadol, zolpidem tartrate, CMA, and MDPV were newly detected in Taiwanese sewage with frequency of 1.4 %− 89.0 %. Conventional drug use typically increased post-pandemic, aside from benzodiazepines and methadone. Methamphetamine showed 100 % frequency, indicating ongoing daily consumption despite COVID-19 measures. Methamphetamine and morphine's consumption dipped then rose around club reopening, hinting at limited access. The consumption trend of methadone appeared to compensate for the use of morphine. Ketamine and NPS demonstrated similar patterns throughout the entire period. NPS as party drugs seemed influenced by an unstable supply chain and complexities in implementation. Benzodiazepines, commonly abused alongside synthetic cathinones in Taiwan exhibited an opposing trend to NPS while aligned with acetaminophen, suggesting elevated stress and anxiety levels during the pandemic. No significant differences were observed in drug consumption between weekdays and weekends, potentially indicating that COVID-19 measures blurred the traditional distinctions between these timeframes. Environmental Implication: New psychoactive substances refer to chemically modified variants of controlled drugs designed to mimic the effects of the original drugs while evading modern detection methods, categorizing them as hazardous materials. The study presents a sewage monitoring project conducted from 2021 to 2024, collecting samples from four WWTPs to analyze NPS and conventional drug trends during and after the COVID-19 pandemic. The findings unc

关键词： COVID-19

WHEN GNNS MEET SYMMETRY IN ILPS: AN ORBIT-BASED FEATURE AUGMENTATION APPROACH

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Qian Li, Lei Li, Qian Wu, Jianghua Wang, Akang Sun, Ruoyu Luo, Xiaodong Chang, Tsung-Hui Shi, Qingjiang School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data China School of Data Science The Chinese University of Hong Kong Shenzhen China School of Artificial Intelligence The Chinese University of Hong Kong Shenzhen China School of Software Engineering Tongji University Shanghai China

A common characteristic in integer linear programs (ILPs) is symmetry, allowing variables to be permuted without altering the underlying problem structure. Recently, GNNs have emerged as a promising approach for solving ILPs. However, a significant challenge arises when applying GNNs to ILPs with symmetry: classic GNN architectures struggle to differentiate between symmetric variables, which limits their predictive accuracy. In this work, we investigate the properties of permutation equivariance and invariance in GNNs, particularly in relation to the inherent symmetry of ILP formulations. We reveal that the interaction between these two factors contributes to the difficulty of distinguishing between symmetric variables. To address this challenge, we explore the potential of feature augmentation and propose several guiding principles for constructing augmented features. Building on these principles, we develop an orbit-based augmentation scheme that first groups symmetric variables and then samples augmented features for each group from a discrete uniform distribution. Empirical results demonstrate that our proposed approach significantly enhances both training efficiency and predictive performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Integer linear programming

An Overview on Machine Learning Methods for Partial Differential Equations: From Physics Informed Neural Networks to Deep Operator Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gonon, Lukas Jentzen, Arnulf Kuckuck, Benno Liang, Siyu Riekert, Adrian von Wurstemberger, Philippe Department of Mathematics Imperial College London United Kingdom School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen [CUHK-Shenzhen China Applied Mathematics: Institute for Analysis and Numerics Faculty of Mathematics and Computer Science University of Münster Germany School of Mathematics and Statistics Nanjing University of Science and Technology Nanjing China School of Data Science The Chinese University of Hong Kong Shenzhen [CUHK-Shenzhen China Mathematisches Institut Ludwig-Maximilians-Universität München Germany Risklab Department of Mathematics ETH Zurich Switzerland

The approximation of solutions of partial differential equations (PDEs) with numerical algorithms is a central topic in applied mathematics. For many decades, various types of methods for this purpose have been developed and extensively studied. One class of methods which has received a lot of attention in recent years are machine learning-based methods, which typically involve the training of artificial neural networks (ANNs) by means of stochastic gradient descent type optimization methods. While approximation methods for PDEs using ANNs have first been proposed in the 1990s they have only gained wide popularity in the last decade with the rise of deep learning. This article aims to provide an introduction to some of these methods and the mathematical theory on which they are based. We discuss methods such as physics-informed neural networks (PINNs) and deep BSDE methods and consider several operator learning approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Partial differential equations

Cloud computing Based POC Diagnostic Device: Rapid Infectious Disease Testing by data Analytics 1

学校读者我要写书评

暂无评论

Cloud Computing Based POC Diagnostic Device: Rapid Infectiou...

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Basha, H. Anwer Ramalingam, L. Hasan, Md Ashfaqul Ananda, M.H. Velmurugan, S. Maniraj, S.P. Saveetha College of Liberal Arts & Sciences Simats University Department of Computer Science Tamil Nadu Chennai India Loyola Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Malla Reddy Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India Reva University School of Electrical and Electronics Engineering Karnataka Bangalore India Tjs Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Srm Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350330915

To meet the growing need for affordable, efficient, and accurate diagnostic tools, the system has developed a Raspberry Pi-based Point-of-Care (POC) gadget for speedy and reliable detection of infectious illnesses. This groundbreaking gadget, built on the flexible and powerful Raspberry Pi computer, ushers in a new era of state-of-the-art POC diagnostics by combining molecular and image analysis methods. Complex testing for pathogens like COVID-19 and malaria may be carried out using this state-of-the-art system, which integrates a camera module and custom biosensors. The device's software parses sensor data, improves diagnostic precision using machine learning techniques, and presents a straightforward interface for clinicians and patients alike. This study takes a holistic approach by considering all relevant factors, including adherence to regulations, user education, upkeep, and data management. Our POC diagnostic gadget driven by a Raspberry Pi provides a low-cost, high-throughput method for diagnosing illness, which may have far-reaching implications for the future of healthcare delivery in both under-resourced and well-endowed regions. © 2023 IEEE.

关键词： Healthcare Infectious Disease Internet of Things, Cloud computing Point-of-Care Diagnostics

Handling Concept Drift in Global Time Series Forecasting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Ziyi Godahewa, Rakshitha Bandara, Kasun Bergmeir, Christoph Department of Data Science and AI Monash University Melbourne Australia School of Computing and Information Systems University of Melbourne Melbourne Australia EnergyAustralia Melbourne Australia

Machine learning (ML) based time series forecasting models often require and assume certain degrees of stationarity in the data when producing forecasts. However, in many real-world situations, the data distributions are not stationary and they can change over time while reducing the accuracy of the forecasting models, which in the ML literature is known as concept drift. Handling concept drift in forecasting is essential for many ML methods in use nowadays, however, the prior work only proposes methods to handle concept drift in the classification domain. To fill this gap, we explore concept drift handling methods in particular for Global Forecasting Models (GFM) which recently have gained popularity in the forecasting domain. We propose two new concept drift handling methods, namely: Error Contribution Weighting (ECW) and Gradient Descent Weighting (GDW), based on a continuous adaptive weighting concept. These methods use two forecasting models which are separately trained with the most recent series and all series, and finally, the weighted average of the forecasts provided by the two models are considered as the final forecasts. Using LightGBM as the underlying base learner, in our evaluation on three simulated datasets, the proposed models achieve significantly higher accuracy than a set of statistical benchmarks and LightGBM baselines across four evaluation metrics. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

DCUDF2: Improving Efficiency and Accuracy in Extracting Zero Level Sets from Unsigned Distance Fields

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Xuhui Yu, Fugang Hou, Fei Wang, Wencheng Zhang, Zhebin He, Ying State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China The OPPO Research Center United States The College of Computing and Data Science Nanyang Technological University Singapore

Unsigned distance fields (UDFs) allow for the representation of models with complex topologies, but extracting accurate zero level sets from these fields poses significant challenges, particularly in preserving topological accuracy and capturing fine geometric details. To overcome these issues, we introduce DCUDF2, an enhancement over DCUDF-the current state-of-the-art method-for extracting zero level sets from UDFs. Our approach utilizes an accuracy-aware loss function, enhanced with self-adaptive weights, to improve geometric quality significantly. We also propose a topology correction strategy that reduces the dependence on hyper-parameter, increasing the robustness of our method. Furthermore, we develop new operations leveraging self-adaptive weights to boost runtime efficiency. Extensive experiments on surface extraction across diverse datasets demonstrate that DCUDF2 outperforms DCUDF and existing methods in both geometric fidelity and topological accuracy. We will make the source code publicly available. © 2024, CC BY.

关键词：