Text-Attributed Graph Representation Learning : Methods, Applications, And Challenges,
2024
Singapore Management University
Text-Attributed Graph Representation Learning : Methods, Applications, And Challenges, Ce Zhang, Menglin Yang, Rex Ying, Hady Wirawan Lauw
Research Collection School Of Computing and Information Systems
Text documents are usually connected in a graph structure, resulting in an important class of data named text-attributed graph, e.g., paper citation graph and Web page hyperlink graph. On the one hand, Graph Neural Networks (GNNs) consider text in each document as general vertex attribute and do not specifically deal with text data. On the other hand, Pre-trained Language Models (PLMs) and Topic Models (TMs) learn effective document embeddings. However, most models focus on text content in each single document only, ignoring link adjacency across documents. The above two challenges motivate the development of text-attributed graph representation learning, combining GNNs …
An Adaptive Large Neighborhood Search For The Multi-Vehicle Profitable Tour Problem With Flexible Compartments And Mandatory Customers,
2024
Singapore Management University
An Adaptive Large Neighborhood Search For The Multi-Vehicle Profitable Tour Problem With Flexible Compartments And Mandatory Customers, Vincent F. Yu, Nabila Yuraisyah Salsabila, Aldy Gunawan, Anggun Nurfitriani Handoko
Research Collection School Of Computing and Information Systems
The home-refill delivery system is a business model that addresses the concerns of plastic waste and its impact on the environment. It allows customers to pick up their household goods at their doorsteps and refill them into their own containers. However, the difficulty in accessing customers’ locations and product consolidations are undeniable challenges. To overcome these issues, we introduce a new variant of the Profitable Tour Problem, named the multi-vehicle profitable tour problem with flexible compartments and mandatory customers (MVPTPFC-MC). The objective is to maximize the difference between the total collected profit and the traveling cost. We model the proposed …
Enhancing Visual Grounding In Vision-Language Pre-Training With Position-Guided Text Prompts,
2024
Singapore Management University
Enhancing Visual Grounding In Vision-Language Pre-Training With Position-Guided Text Prompts, Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Shuicheng Yan
Research Collection School Of Computing and Information Systems
Vision-Language Pre-Training (VLP) has demonstrated remarkable potential in aligning image and text pairs, paving the way for a wide range of cross-modal learning tasks. Nevertheless, we have observed that VLP models often fall short in terms of visual grounding and localization capabilities, which are crucial for many downstream tasks, such as visual reasoning. In response, we introduce a novel Position-guided Text Prompt ( PTP ) paradigm to bolster the visual grounding abilities of cross-modal models trained with VLP. In the VLP phase, PTP divides an image into N x N blocks and employs a widely-used object detector to identify objects …
Evaluation Of Orca 2 Against Other Llms For Retrieval Augmented Generation,
2024
Singapore Management University
Evaluation Of Orca 2 Against Other Llms For Retrieval Augmented Generation, Donghao Huang, Zhaoxia Wang
Research Collection School Of Computing and Information Systems
This study presents a comprehensive evaluation of Microsoft Research’s Orca 2, a small yet potent language model, in the context of Retrieval Augmented Generation (RAG). The research involved comparing Orca 2 with other significant models such as Llama-2, GPT-3.5-Turbo, and GPT-4, particularly focusing on its application in RAG. Key metrics, included faithfulness, answer relevance, overall score, and inference speed, were assessed. Experiments conducted on high-specification PCs revealed Orca 2’s exceptional performance in generating high quality responses and its efficiency on consumer-grade GPUs, underscoring its potential for scalable RAG applications. This study highlights the pivotal role of smaller, efficient models like …
Reinforcement Learning With Maskable Stock Representation For Portfolio Management In Customizable Stock Pools,
2024
Singapore Management University
Reinforcement Learning With Maskable Stock Representation For Portfolio Management In Customizable Stock Pools, Wentao Zhang, Yilei Zhao, Shuo Sun, Jie Ying, Yonggang Xie, Zitao Song, Xinrun Wang, Bo An
Research Collection School Of Computing and Information Systems
Portfolio management (PM) is a fundamental financial trading task, which explores the optimal periodical reallocation of capitals into different stocks to pursue long-term profits. Reinforcement learning (RL) has recently shown its potential to train profitable agents for PM through interacting with financial markets. However, existing work mostly focuses on fixed stock pools, which is inconsistent with investors’ practical demand. Specifically, the target stock pool of different investors varies dramatically due to their discrepancy on market states and individual investors may temporally adjust stocks they desire to trade (e.g., adding one popular stocks), which lead to customizable stock pools (CSPs). Existing …
Grasper: A Generalist Pursuer For Pursuit-Evasion Problems,
2024
Singapore Management University
Grasper: A Generalist Pursuer For Pursuit-Evasion Problems, Pengdeng Li, Shuxin Li, Xinrun Wang, Jakub Cerny, Youzhi Zhang, Stephen Mcaleer, Hau Chan, Bo An
Research Collection School Of Computing and Information Systems
Pursuit-evasion games (PEGs) model interactions between a team of pursuers and an evader in graph-based environments such as urban street networks. Recent advancements have demonstrated the effectiveness of the pre-training and fine-tuning paradigm in Policy-Space Response Oracles (PSRO) to improve scalability in solving large-scale PEGs. However, these methods primarily focus on specific PEGs with fixed initial conditions that may vary substantially in real-world scenarios, which significantly hinders the applicability of the traditional methods. To address this issue, we introduce Grasper, a GeneRAlist purSuer for Pursuit-Evasion pRoblems, capable of efficiently generating pursuer policies tailored to specific PEGs. Our contributions are threefold: …
Reinforcement Retrieval Leveraging Fine-Grained Feedback For Fact Checking News Claims With Black-Box Llm,
2024
Singapore Management University
Reinforcement Retrieval Leveraging Fine-Grained Feedback For Fact Checking News Claims With Black-Box Llm, Xuan Zhang, Wei Gao
Research Collection School Of Computing and Information Systems
Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents …
Discovering Personalized Characteristic Communities In Attributed Graphs,
2024
Singapore Management University
Discovering Personalized Characteristic Communities In Attributed Graphs, Yudong Niu, Yuchen Li, Panagiotis Karras, Yanhao Wang, Zhao Li
Research Collection School Of Computing and Information Systems
What is the widest community in which a person exercises a strong impact? Although extensive attention has been devoted to searching communities containing given individuals, the problem of finding their unique communities of influence has barely been examined. In this paper, we study the novel problem of Characteristic cOmmunity Discovery (COD) in attributed graphs. Our goal is to identify the largest community, taking into account the query attribute, in which the query node has a significant impact. The key challenge of the COD problem is that it requires evaluating the influence of the query node over a large number of …
Cornac-Ab : An Open-Source Recommendation Framework With Native A/B Testing Integration,
2024
Singapore Management University
Cornac-Ab : An Open-Source Recommendation Framework With Native A/B Testing Integration, Rong Sheng Ong, Quoc Tuan Truong, Hady Wirawan Lauw
Research Collection School Of Computing and Information Systems
Recommender systems significantly impact user experience across diverse domains, yet existing frameworks often prioritize offline evaluation metrics, neglecting the crucial integration of A/B testing for forward-looking assessments. In response, this paper introduces a new framework seamlessly incorporating A/B testing into the Cornac recommendation library. Leveraging a diverse collection of model implementations in Cornac, our framework enables effortless A/B testing experiment setup from offline trained models. We introduce a carefully designed dashboard and a robust backend for efficient logging and analysis of user feedback. This not only streamlines the A/B testing process but also enhances the evaluation of recommendation models in …
Term Importance For Transformer-Based Qa Retrieval : A Case Study Of Stackexchange,
2024
Singapore Management University
Term Importance For Transformer-Based Qa Retrieval : A Case Study Of Stackexchange, Bryan Zhi Yang Tan, Hady W. Lauw
Research Collection School Of Computing and Information Systems
Question-answering (QA) retrieval is the task of retrieving the most relevant answer to a given question from a collection of answers. Various approaches to QA retrieval have been developed recently. One successful and popular model is Contextualized Late Interaction over BERT (ColBERT), a transformer-based approach that adopts a query-document scoring mechanism that retains the granularity of transformer matching, whilst improving on efficiency. However, one key limitation is that it requires further fine-tuning for new query or collection types. In this work, we explore and propose several non-parametric retrieval augmentation methods based on explicit signals of term importance that improve over …
Finding Combinatorial Patterns In Real Valued Omics Data,
2024
University of Missouri-St. Louis
Finding Combinatorial Patterns In Real Valued Omics Data, Kenneth Smith
Dissertations
Precision medicine is a healthcare approach which tailors disease prevention and treatment to an individual, based on their genetics, environment, lifestyle, and physiological state. These factors interact to produce biological changes that can be measured to produce data called omics, and include genomics, lipidomics, and proteomics. Despite the abundance of omics data and analysis techniques, researchers still struggle to identify biological findings that replicate across data sets and translate into clinical applications. In this dissertation, we employ combinatorial optimization techniques to improve upon three steps in the precision medicine analysis pipeline: 1) data cleaning, 2) community detection, and 3) feature …
Accessing Advanced National Supercomputing And Storage Resources For Computational Research,
2024
Kennesaw State University
Accessing Advanced National Supercomputing And Storage Resources For Computational Research, Ramazan Aygun
All Things Open
This presentation will cover ACCESS (Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support), and Kennesaw State University's involvement in Open Science Data Federation program as a data origin to help researchers and educators with or without supporting grants to utilize the nation’s advanced computing systems and services. ACCESS, a program established and funded by the National Science Foundation, is an ecosystem with capabilities for new modes of research and further democratizing participation. The presentation covers how to apply for allocations on ACCESS. The last part of the presentation will briefly explain Open Science Data Federation and Kennesaw State University's involvement as …
Enhancing Evolutionary Computation: Optimizing Phylogeny-Informed Fitness Estimation Through Strategic Modifications,
2024
University of Minnesota - Morris
Enhancing Evolutionary Computation: Optimizing Phylogeny-Informed Fitness Estimation Through Strategic Modifications, Chenfei Peng, Nic Mcphee
Undergraduate Research Symposium 2024
In evolutionary computation, programs are developed using evolution's basic principles, such as selection, mutation, and recombination, to iteratively improve problem solutions towards optimal outcomes in a reasonable amount of time. To save time and be more efficient, we are currently exploring a modified version of phylogeny-informed fitness estimation. The original version evaluates each individual program on a subset of the training cases and estimates the performance everywhere else according to its parent's performance. Our approach involves comprehensive evaluation of promising programs across all training cases, increasing computational investment where the sub-sampled results indicated potential gains. This method led to our …
Hyper-Heuristic Approach With K-Means Clustering For Inter-Cell Scheduling,
2024
School of Mathematics and Computer Science, Yan'an University, Yan'an 716000, China
Hyper-Heuristic Approach With K-Means Clustering For Inter-Cell Scheduling, Yanlin Zhao, Yunna Tian
Journal of System Simulation
Abstract: According to the actual production situation of China's manufacturing industry, a hyperheuristic algorithm based on K-means clustering is proposed for inter-cell scheduling problem of flexible job-shop. K-means clustering is applied to group entities with similar attributes into the corresponding work cluster decision blocks, and the ant colony algorithm is used to select heuristic rules for each decision block. The optimal scheduling solutions are generated by using corresponding heuristic rules for scheduling of entities in each decision block. Computational results show that, the computational granularity is properly increased by the form of decision blocks, and the computational efficiency of the …
Distributed Energy Management Strategy Of Microgrid Based On Master-Slave Game,
2024
School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
Distributed Energy Management Strategy Of Microgrid Based On Master-Slave Game, Miaomiao Ma, Hao Wang, Lipeng Dong, Xiangjie Liu
Journal of System Simulation
Abstract: Under the operation mode of power market, based on two-layer master-slave game, a distributed energy management strategy for the microgrid is proposed to tackle the conflict between the overall optimal operation of renewable microgrid and the maximum profit of each investor. To fully consider the balance between energy supply and demand, the concept of power trading agent is introduced, and an integrated demand response strategy based on consumer satisfaction and adjustable load is proposed on the user side. Considering the initiative and decision-making ability of power supply and load, the decision-making game model is established with power trading agent …
Optimization Of Urban Traffic Microsimulation Model For Carbon Emission Reduction,
2024
Beijing City Interface Technology Co., Ltd., Beijing 100045, China; School of Civil and Transportation Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China
Optimization Of Urban Traffic Microsimulation Model For Carbon Emission Reduction, Bo Liu, Jianxin Lin, Yini Liu, Dong Zhang
Journal of System Simulation
Abstract: To assess the environmental benefits of transportation management or control strategies, a method to effectively integrate the micro-traffic simulation model and the micro-vehicle emission model is proposed. VISSIM platform is used to build a case micro traffic simulation model. K-means clustering method is used to divide the driving behavior into 4 types based on the acceleration and deceleration characteristics of different speed intervals of the trajectory data, and the global parameters of the simulation model are calibrated based on the driving characteristics, which quantitatively describe the total sensitivity of the parameters and the sensitivity of the interactions between the …
Modeling And Analysis Of Hybrid Traffic Flow Considering Actual Behavior Of Platoon,
2024
Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China
Modeling And Analysis Of Hybrid Traffic Flow Considering Actual Behavior Of Platoon, Xi Wang, Xiujian Yang, Xiaohan Jia, Shenyi Wang
Journal of System Simulation
Abstract: To explore the effect of actual behavior of autonomous vehicular platoon on traffic flow, aiming at the hybrid traffic flow mixed with predecessor following(PF) platoon which is modeled according to the actual control strategy, a hybrid traffic flow model is established based on cellular automata(CA) modeling method. Simulation analysis shows that the effect of platoon characteristics such as time headway, market penetration, platoon size, and control gains on hybrid traffic flow presents coupling and nonlinear properties. The spatiotemporal behavior of hybrid traffic flow with different platoon characteristics is generally much different. Reducing time headway or increasing platoon market penetration …
Dynamic Path Planning For Mobile Robot Based On Rrt* And Dynamic Window Approach,
2024
Nanjing University of Information Science &Technology, Nanjing 210000, China
Dynamic Path Planning For Mobile Robot Based On Rrt* And Dynamic Window Approach, Rui Zhang, Li Zhou, Zhengyang Liu
Journal of System Simulation
Abstract: A dynamic path planning method combining RRT* and dynamic window approach(DWA) is proposed to realize the obstacle avoidance of mobile robot in complex environment of dynamic obstacles. Improved RRT* algorithm is used to generate the global optimal safe path based on the known environment information. By eliminating the dangerous nodes generated by RRT* algorithm, the security of global path is ensured. Greedy algorithm is used to remove the redundant nodes in the path to reduce the length of global path. DWA is used to track along the global optimal path planned by the improved RRT* algorithm. When static obstacles …
Collaborative Navigation Method For 5g Cluster Uav Based On Configuration Optimization,
2024
State Grid Jiangsu Electric Power Co., Ltd., Nanjing 210024, China
Collaborative Navigation Method For 5g Cluster Uav Based On Configuration Optimization, Chao Gao, Zheng Huang, Xuan Zhao, Hongxing Wang, Tao Long
Journal of System Simulation
Abstract: The existing range based cooperative navigation methods for clustered UAVs generally ignore the impact of space configuration on positioning and energy determination, which makes it difficult to obtain the accurate navigation and positioning results. In view of this, a collaborative navigation method is proposed for 5G clustered UAVs based on spatial configuration optimization. The relative ranging error model of UAVs based on 5G signals in complex environments is constructed, and the optimization strategy for collaborative navigation nodes is established based on the minimum geometric division of precision(GDOP) criterion to achieve the real-time optimization of collaborative navigation spatial configuration; A …
Incremental Image Dehazing Algorithm Based On Multiple Transfer Attention,
2024
Zhengzhou Hengda Intelligent Control Technology Company Limited, Zhengzhou 450000, China
Incremental Image Dehazing Algorithm Based On Multiple Transfer Attention, Jinyang Wei, Keping Wang, Yi Yang, Shumin Fei
Journal of System Simulation
Abstract: In order to improve the processing ability of the depth-neural network dehazing algorithm to the supplementary data set, and to make the network differently process the image features of different importance to improve the dehazing ability of the network, an incremental dehazing algorithm based on multiple migration of attention is proposed. The teacher's attention generation network in the form of Encoder-Decoder extracts the multiple attention of labels and haze, which is used it as the label of the characteristic migration media network to constrain the network training to form the migration media attention as close as possible to the …
