检索结果-内蒙古大学图书馆

Uncovering Neural Scaling Laws in Molecular Representation Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Dingshuo Zhu, Yanqiao Zhang, Jieyu Du, Yuanqi Li, Zhixun Liu, Qiang Wu, Shu Wang, Liang Center for Research on Intelligent Perception and Computing Institute of Automation Chinese Academy of Sciences China Department of Computer Science University of California Los Angeles United States The Paul G. Allen School of Computer Science and Engineering University of Washington United States Department of Computer Science Cornell University United States Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong

Molecular Representation Learning (MRL) has emerged as a powerful tool for drug and materials discovery in a variety of tasks such as virtual screening and inverse design. While there has been a surge of interest in advancing model-centric techniques, the influence of both data quantity and quality on molecular representations is not yet clearly understood within this field. In this paper, we delve into the neural scaling behaviors of MRL from a data-centric viewpoint, examining four key dimensions: (1) data modalities, (2) dataset splitting, (3) the role of pre-training, and (4) model capacity. Our empirical studies confirm a consistent power-law relationship between data volume and MRL performance across these dimensions. Additionally, through detailed analysis, we identify potential avenues for improving learning efficiency. To challenge these scaling laws, we adapt seven popular data pruning strategies to molecular data and benchmark their performance. Our findings underline the importance of data-centric MRL and highlight possible directions for future research. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

Deep multiple instance learning on heterogeneous graph for drug–disease association prediction

学校读者我要写书评

暂无评论

computers in Biology and Medicine 2025年 184卷 109403-109403页

作者： Gu, Yaowen Zheng, Si Zhang, Bowen Kang, Hongyu Jiang, Rui Li, Jiao Beijing100020 China Department of Chemistry New York University NY10027 United States Institute for Artificial Intelligence Department of Computer Science and Technology BNRist Tsinghua University Beijing100084 China Beijing StoneWise Technology Co Ltd. Beijing100080 China Ministry of Education Key Laboratory of Bioinformatics Bioinformatics Division at the Beijing National Research Center for Information Science and Technology Center for Synthetic and Systems Biology Department of Automation Tsinghua University Beijing100084 China

Drug repositioning offers promising prospects for accelerating drug discovery by identifying potential drug–disease associations (DDAs) for existing drugs and diseases. Previous methods have generated meta-path-augmented node or graph embeddings for DDA prediction in drug–disease heterogeneous networks. However, these approaches rarely develop end-to-end frameworks for path instance-level representation learning as well as the further feature selection and aggregation. By leveraging the abundant topological information in path instances, more fine-grained and interpretable predictions can be achieved. To this end, we introduce deep multiple instance learning into drug repositioning by proposing a novel method called MilGNet. MilGNet employs a heterogeneous graph neural network (HGNN)-based encoder to learn drug and disease node embeddings. Treating each drug–disease pair as a bag, we designed a special quadruplet meta-path form and implemented a pseudo meta-path generator in MilGNet to obtain multiple meta-path instances based on network topology. Additionally, a bidirectional instance encoder enhances the representation of meta-path instances. Finally, MilGNet utilizes a multi-scale interpretable predictor to aggregate bag embeddings with an attention mechanism, providing predictions at both the bag and instance levels for accurate and explainable predictions. Comprehensive experiments on five benchmarks demonstrate that MilGNet significantly outperforms ten advanced methods. Notably, three case studies on one drug (Methotrexate) and two diseases (Renal Failure and Mismatch Repair Cancer Syndrome) highlight MilGNet's potential for discovering new indications, therapies, and generating rational meta-path instances to investigate possible treatment mechanisms. The source code is available at https://***/gu-yaowen/MilGNet. © 2024 Elsevier Ltd

关键词： Graph embeddings

An Experimental research on Temperature Accuracy Algorithm in Fan Coil Thermostat

学校读者我要写书评

暂无评论

An Experimental Research on Temperature Accuracy Algorithm i...

China International Electrical and Energy Conference (CIEEC)

作者： Yunus Arı Ergün Cücük Seda Karateke Electric and Electronic Engineering Institute of Graduate Studies Istanbul University - Cerrahpaşa Istanbul Turkey Department of Research and Development Ges Teknik Air Conditioning Control and Automation Systems Industry and Trade Inc. Istanbul Turkey Department of Computer Engineering Faculty of Engineering Istanbul Topkapı University Istanbul Turkey

The efficient operation of HVAC&R systems are based on keeping indoor temperature and air quality at an optimum level without disturbing comfort. Starting from this point, in this experimental research, the factors affecting the measurement accuracy during the room temperature detection of a wall mount fan coil thermostat were examined. Among the external effects, the effect of the device components on the measurement was focused and the solution of the measurement deviations occurred in this extent was investigated. Based on the experiments, the algorithm that must be applied to reach the optimum temperature measurement of a room thermostat developed for Fan Coil systems was proposed.

关键词：

Short - Term Prediction of Coke Pushing Current Peak Based on Improved ARIMA Model

学校读者我要写书评

暂无评论

Short - Term Prediction of Coke Pushing Current Peak Based o...

Industrial Cyber-Physical systems (ICPS)

作者： Haiyang Wei Luefeng Chen Jie Hu Yi Ren Min Wu Witold Pedrycz Kaoru Hirota School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Tokyo Institute of Technology Yokohama Japan

Coke pushing current is an indicator to evaluate the difficulty of coke pushing operation. The higher coke pushing current is, the greater coke pushing resistance is, and the more difficult coke is to push out. Accurate prediction of current peak during future coke pushing operation can provide more time for production personnel to adjust production status and avoid difficult coke pushing in carbonization chamber. In this paper, a combination prediction model based on VMD (Variational Mode Decomposition) and improved ARIMA (Autoregressive Integrated Moving Average) models is proposed. Firstly, VMD algorithm is used to decompose time series of coke pushing current peak, de-noising data, and extracting main information of time series. Then, ARIMA model is used to predict mean change of linear elasticity and GARCH (Generalized Autore-gressive Conditional Heteroskedasticity) model is introduced to predict ARIMA model residual and improve heteroscedasticity of nonlinear part of time series, and then ARIMA-GARCH model is established. Finally, predicted value is obtained by the sum of each component prediction. The experimental results show that the proposed prediction model has a high prediction accuracy in the short-term prediction of coke pushing current peak. The scheme is applied to actual coking production to guide production of coke.

关键词： Resistance Ovens Time series analysis Noise reduction Production Predictive models Prediction algorithms

Infusing Model Predictive Control into Meta-Reinforcement Learning for Mobile Robots in Dynamic Environments

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shin, Jaeuk Hakobyan, Astghik Park, Mingyu Kim, Yeoneung Kim, Gihun Yang, Insoon The Department of Electrical and Computer Engineering Automation and Systems Research Institute Seoul National University Seoul08826 Korea Republic of

The successful operation of mobile robots requires them to adapt rapidly to environmental changes. To develop an adaptive decision-making tool for mobile robots, we propose a novel algorithm that combines meta-reinforcement learning (meta-RL) with model predictive control (MPC). Our method employs an off-policy meta-RL algorithm as a baseline to train a policy using transition samples generated by MPC when the robot detects certain events that can be effectively handled by MPC, with its explicit use of robot dynamics. The key idea of our method is to switch between the meta-learned policy and the MPC controller in a randomized and event-triggered fashion to make up for suboptimal MPC actions caused by the limited prediction horizon. During meta-testing, the MPC module is deactivated to significantly reduce computation time in motion control. We further propose an online adaptation scheme that enables the robot to infer and adapt to a new task within a single trajectory. The performance of our method has been demonstrated through simulations using a nonlinear car-like vehicle model with (i) synthetic movements of obstacles, and (ii) real-world pedestrian motion data. The simulation results indicate that our method outperforms other algorithms in terms of learning efficiency and navigation quality. Copyright © 2021, The Authors. All rights reserved.

关键词： Model predictive control

On anderson acceleration for partially observable Markov decision processes

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ermis, Melike Park, Mingyu Yang, Insoon The Department of Electrical and Computer Engineering Automation and Systems Research Institute Seoul National University Seoul08826 Korea Republic of

This paper proposes an accelerated method for approximately solving partially observable Markov decision process (POMDP) problems offline. Our method carefully combines two existing tools: Anderson acceleration (AA) and the fast informed bound (FIB) method. Adopting AA, our method rapidly solves an approximate Bellman equation with an efficient combination of previous solution estimates. Furthermore, the use of FIB alleviates the scalability issue inherent in POMDPs. We show the convergence of the overall algorithm to the suboptimal solution obtained by FIB. We further consider a simulation-based method and prove that the approximation error is bounded explicitly. The performance of our algorithm is evaluated on several benchmark problems. The results of our experiments demonstrate that the proposed algorithm converges significantly faster without degrading the quality of the solution compared to its standard counterpart. Copyright © 2021, The Authors. All rights reserved.

关键词： Markov processes

Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hakobyan, Astghik Yang, Insoon Department of Electrical and Computer Engineering Automation and Systems Research Institute Seoul National University Seoul08826 Korea Republic of

This paper proposes a novel safety specification tool, called the distributionally robust risk map (DR-risk map), for a mobile robot operating in a learning-enabled environment. Given the robot's position, the map aims to reliably assess the conditional value-at-risk (CVaR) of collision with obstacles whose movements are inferred by Gaussian process regression (GPR). Unfortunately, the inferred distribution is subject to errors, making it difficult to accurately evaluate the CVaR of collision. To overcome this challenge, this tool measures the risk under the worst-case distribution in a so-called ambiguity set that characterizes allowable distribution errors. To resolve the infinite-dimensionality issue inherent in the construction of the DR-risk map, we derive a tractable semidefinite programming formulation that provides an upper bound of the risk, exploiting techniques from modern distributionally robust optimization. As a concrete application for motion planning, a distributionally robust RRT* algorithm is considered using the risk map that addresses distribution errors caused by GPR. Furthermore, a motion control method is devised using the DR-risk map in a learning-based model predictive control (MPC) formulation. In particular, a neural network approximation of the risk map is proposed to reduce the computational cost in solving the MPC problem. The performance and utility of the proposed risk map are demonstrated through simulation studies that show its ability to ensure the safety of mobile robots despite learning errors. Copyright © 2021, The Authors. All rights reserved.

关键词： Model predictive control

Distributional robustness in minimax linear quadratic control with wasserstein distance

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kim, Kihyun Yang, Insoon Department of Electrical and Computer Engineering Automation and Systems Research Institute Seoul National University Seoul08826 Korea Republic of

To address the issue of inaccurate distributions in practical stochastic systems, a minimax linear-quadratic control method is proposed using the Wasserstein metric. Our method aims to construct a control policy that is robust against errors in an empirical distribution of underlying uncertainty, by adopting an adversary that selects the worst-case distribution. The opponent receives a Wasserstein penalty proportional to the amount of deviation from the empirical distribution. A closed-form expression of the finite-horizon optimal policy pair is derived using a Riccati equation. The result is then extended to the infinite-horizon average cost setting by identifying conditions under which the Riccati recursion converges to the unique positive semi-definite solution to an algebraic Riccati equation. Our method is shown to possess several salient features including closed-loop stability, and an out-of-sample performance guarantee. We also discuss how to optimize the penalty parameter for enhancing the distributional robustness of our control policy. Last but not least, a theoretical connection to the classical H∞-method is identified from the perspective of distributional robustness. Copyright © 2021, The Authors. All rights reserved.

关键词： Linear control systems

Label Informed Contrastive Pretraining for Node Importance Estimation on Knowledge Graphs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Tianyu Hou, Chengbin Jiang, Rui Zhang, Xuegong Zhou, Chenghu Tang, Ke Lv, Hairong The Ministry of Education Key Laboratory of Bioinformatics Bioinformatics Division Beijing National Research Center for Information Science and Technology Department of Automation Tsinghua University Beijing100084 China The School of Computer Science and Engineering Fuyao Institute of Technology Fuzhou350109 China The State Key Laboratory of Resources and Environmental Information Systems Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China The Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Fuzhou Institute of Data Technology Fuzhou350200 China

Node Importance Estimation (NIE) is a task of inferring importance scores of the nodes in a graph. Due to the availability of richer data and knowledge, recent research interests of NIE have been dedicating to knowledge graphs for predicting future or missing node importance scores. Existing state-of-the-art NIE methods train the model by available labels, and they consider every interested node equally before training. However, the nodes with higher importance often require or receive more attention in real-world scenarios, e.g., people may care more about the movies or webpages with higher importance. To this end, we introduce Label Informed ContrAstive Pretraining (LICAP) to the NIE problem for being better aware of the nodes with high importance scores. Specifically, LICAP is a novel type of contrastive learning framework that aims to fully utilize the continuous labels to generate contrastive samples for pretraining embeddings. Considering the NIE problem, LICAP adopts a novel sampling strategy called top nodes preferred hierarchical sampling to first group all interested nodes into a top bin and a non-top bin based on node importance scores, and then divide the nodes within top bin into several finer bins also based on the scores. The contrastive samples are generated from those bins, and are then used to pretrain node embeddings of knowledge graphs via a newly proposed Predicate-aware Graph Attention Networks (PreGAT), so as to better separate the top nodes from non-top nodes, and distinguish the top nodes within top bin by keeping the relative order among finer bins. Extensive experiments demonstrate that the LICAP pretrained embeddings can further boost the performance of existing NIE methods and achieve the new state-of-the-art performance regarding both regression and ranking metrics. The source code for reproducibility is available at https://***/zhangtia16/LICAP Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph