Learning Comprehensive Global Features In Person Re-Identification: Ensuring Discriminativeness Of More Local Regions,
2023
Shanghai Jiaotong University
Learning Comprehensive Global Features In Person Re-Identification: Ensuring Discriminativeness Of More Local Regions, Jiali Xia, Jianqiang Huang, Shibao Zheng, Qin Zhou, Bernt Schiele, Xian-Sheng Hua, Qianru Sun
Research Collection School Of Computing and Information Systems
Person re-identification (Re-ID) aims to retrieve person images from a large gallery given a query image of a person of interest. Global information and fine-grained local features are both essential for the representation. However, global embedding learned by naive classification model tends to be trapped in the most discriminative local region, leading to poor evaluation performance. To address the issue, we propose a novel baseline network that learns strong global feature termed as Comprehensive Global Embedding (CGE), ensuring more local regions of global feature maps to be discriminative. In this work, two key modules are proposed including Non-parameterized Local Classifier …
Real-Time Hierarchical Map Segmentation For Coordinating Multi-Robot Exploration,
2023
Singapore Management University
Real-Time Hierarchical Map Segmentation For Coordinating Multi-Robot Exploration, Tianze Luo, Zichen Chen, Budhitama Subagdja, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
Coordinating a team of autonomous agents to explore an environment can be done by partitioning the map of the environment into segments and allocating the segments as targets for the individual agents to visit. However, given an unknown environment, map segmentation must be conducted in a continuous and incremental manner. In this paper, we propose a novel real-time hierarchical map segmentation method for supporting multi-agent exploration of indoor environments, wherein clusters of regions of segments are formed hierarchically from randomly sampled points in the environment. Each cluster is then assigned with a cost-utility value based on the minimum cost possible …
Mirror: Mining Implicit Relationships Via Structure-Enhanced Graph Convolutional Networks,
2023
Singapore Management University
Mirror: Mining Implicit Relationships Via Structure-Enhanced Graph Convolutional Networks, Jiaying Liu, Feng Xia, Jing Ren, Bo Xu, Guansong Pang, Lianhua Chi
Research Collection School Of Computing and Information Systems
Data explosion in the information society drives people to develop more effective ways to extract meaningful information. Extracting semantic information and relational information has emerged as a key mining primitive in a wide variety of practical applications. Existing research on relation mining has primarily focused on explicit connections and ignored underlying information, e.g., the latent entity relations. Exploring such information (defined as implicit relationships in this article) provides an opportunity to reveal connotative knowledge and potential rules. In this article, we propose a novel research topic, i.e., how to identify implicit relationships across heterogeneous networks. Specially, we first give a …
Cross-Domain Graph Anomaly Detection Via Anomaly-Aware Contrastive Alignment,
2023
Singapore Management University
Cross-Domain Graph Anomaly Detection Via Anomaly-Aware Contrastive Alignment, Qizhou Wang, Guansong Pang, Mahsa Salehi, Wray Buntine, Christopher Leckie
Research Collection School Of Computing and Information Systems
Cross-domain graph anomaly detection (CD-GAD) describes the problem of detecting anomalous nodes in an unlabelled target graph using auxiliary, related source graphs with labelled anomalous and normal nodes. Although it presents a promising approach to address the notoriously high false positive issue in anomaly detection, little work has been done in this line of research. There are numerous domain adaptation methods in the literature, but it is difficult to adapt them for GAD due to the unknown distributions of the anomalies and the complex node relations embedded in graph data. To this end, we introduce a novel domain adaptation approach, …
Alignment-Enriched Tuning For Patch-Level Pre-Trained Document Image Models,
2023
Singapore Management University
Alignment-Enriched Tuning For Patch-Level Pre-Trained Document Image Models, Lei Wang, Jiabang He, Xing Xu, Ning Liu, Hui Liu
Research Collection School Of Computing and Information Systems
Alignment between image and text has shown promising im provements on patch-level pre-trained document image mod els. However, investigating more effective or finer-grained alignment techniques during pre-training requires a large amount of computation cost and time. Thus, a question natu rally arises: Could we fine-tune the pre-trained models adap tive to downstream tasks with alignment objectives and achieve comparable or better performance? In this paper, we pro pose a new model architecture with alignment-enriched tuning (dubbed AETNet) upon pre-trained document image models, to adapt downstream tasks with the joint task-specific super vised and alignment-aware contrastive objective. Specifically, weintroduce an extra …
Mitigating Popularity Bias For Users And Items With Fairness-Centric Adaptive Recommendation,
2023
Singapore Management University
Mitigating Popularity Bias For Users And Items With Fairness-Centric Adaptive Recommendation, Zhongzhou Liu, Yuan Fang, Min Wu
Research Collection School Of Computing and Information Systems
Recommendation systems are popular in many domains. Researchers usually focus on the effectiveness of recommendation (e.g., precision) but neglect the popularity bias that may affect the fairness of the recommendation, which is also an important consideration that could influence the benefits of users and item providers. A few studies have been proposed to deal with the popularity bias, but they often face two limitations. Firstly, most studies only consider fairness for one side - either users or items, without achieving fairness jointly for both. Secondly, existing methods are not sufficiently tailored to each individual user or item to cope with …
On Generalized Degree Fairness In Graph Neural Networks,
2023
Singapore Management University
On Generalized Degree Fairness In Graph Neural Networks, Zemin Liu, Trung Kien Nguyen, Yuan Fang
Research Collection School Of Computing and Information Systems
Conventional graph neural networks (GNNs) are often confronted with fairness issues that may stem from their input, including node attributes and neighbors surrounding a node. While several recent approaches have been proposed to eliminate the bias rooted in sensitive attributes, they ignore the other key input of GNNs, namely the neighbors of a node, which can introduce bias since GNNs hinge on neighborhood structures to generate node representations. In particular, the varying neighborhood structures across nodes, manifesting themselves in drastically different node degrees, give rise to the diverse behaviors of nodes and biased outcomes. In this paper, we first define …
Flexible Job-Shop Scheduling Via Graph Neural Network And Deep Reinforcement Learning,
2023
Singapore Management University
Flexible Job-Shop Scheduling Via Graph Neural Network And Deep Reinforcement Learning, Wen Song, Xinyang Chen, Qiqiang Li, Zhiguang Cao
Research Collection School Of Computing and Information Systems
Recently, deep reinforcement learning (DRL) has been applied to learn priority dispatching rules (PDRs) for solving complex scheduling problems. However, the existing works face challenges in dealing with flexibility, which allows an operation to be scheduled on one out of multiple machines and is often required in practice. Such one-to-many relationship brings additional complexity in both decision making and state representation. This article considers the well-known flexible job-shop scheduling problem and addresses these issues by proposing a novel DRL method to learn high-quality PDRs end to end. The operation selection and the machine assignment are combined as a composite decision. …
Scalable And Globally Optimal Generalized L1 K-Center Clustering Via Constraint Generation In Mixed Integer Linear Programming,
2023
Singapore Management University
Scalable And Globally Optimal Generalized L1 K-Center Clustering Via Constraint Generation In Mixed Integer Linear Programming, Aravinth Chembu, Scott Sanner, Hassan Khurram, Akshat Kumar
Research Collection School Of Computing and Information Systems
The k-center clustering algorithm, introduced over 35 years ago, is known to be robust to class imbalance prevalent in many clustering problems and has various applications such as data summarization, document clustering, and facility location determination. Unfortunately, existing k-center algorithms provide highly suboptimal solutions that can limit their practical application, reproducibility, and clustering quality. In this paper, we provide a novel scalable and globally optimal solution to a popular variant of the k-center problem known as generalized L1 k-center clustering that uses L1 distance and allows the selection of arbitrary vectors as cluster centers. We show that this clustering objective …
Future Aware Pricing And Matching For Sustainable On-Demand Ride Pooling,
2023
Singapore Management University
Future Aware Pricing And Matching For Sustainable On-Demand Ride Pooling, Xianjie Zhang, Pradeep Varakantham, Hao Jiang
Research Collection School Of Computing and Information Systems
The popularity of on-demand ride pooling is owing to the benefits offered to customers (lower prices), taxi drivers (higher revenue), environment (lower carbon footprint due to fewer vehicles) and aggregation companies like Uber (higher revenue). To achieve these benefits, two key interlinked challenges have to be solved effectively: (a) pricing – setting prices to customer requests for taxis; and (b) matching – assignment of customers (that accepted the prices) to taxis/cars. Traditionally, both these challenges have been studied individually and using myopic approaches (considering only current requests), without considering the impact of current matching on addressing future requests. In this …
The Application Of Graph Technology For Improving Entity Resolution Results In The Context Of Group Membership,
2023
University of Arkansas Little Rock
The Application Of Graph Technology For Improving Entity Resolution Results In The Context Of Group Membership, Md Abdus Salam Siddique
Theses and Dissertations
The main objective of Entity resolution (ER) is to find duplicate records within the same data table from the same source or different data tables from various sources. A traditional pair-wise supervised entity resolution matching depends on pre-built rules for finding matched records. On the other hand, unsupervised or semisupervised also relies on pair-wise matching. In the maximum case, group membership is left behind for consideration. In this dissertation, I have discussed the design, implementation and evaluation of a graph-based entity resolution for group membership to enhance the pair-wise matching ER system. I have designed and implemented a pipeline for …
Integrated Organizational Machine Learning For Aviation Flight Data,
2023
Kansas State University
Integrated Organizational Machine Learning For Aviation Flight Data, Michael J. Pritchard, Paul Thomas, Eric Webb, Jon Martin, Austin Walden
National Training Aircraft Symposium (NTAS)
An increased availability of data and computing power has allowed organizations to apply machine learning techniques to various fleet monitoring activities. Additionally, our ability to acquire aircraft data has increased due to the miniaturization of small form factor computing machines. Aircraft data collection processes contain many data features in the form of multivariate time-series (continuous, discrete, categorical, etc.) which can be used to train machine learning models. Yet, three major challenges still face many flight organizations 1) integration and automation of data collection frameworks, 2) data cleanup and preparation, and 3) embedded machine learning framework. Data cleanup and preparation has …
Development Of Open-Source Software 'Pystage',
2023
Calvin University
Development Of Open-Source Software 'Pystage', Victor T. Norman, Brandon Husted, Zhonglin 'Loya' Niu
Summer Research
PyStage is an open-source project that seeks to help students bridge the gap between block-based programming in Scratch and text-based programming in Python.
A New Credit Scoring Model To Reduce Potential Predatory Lending: A Design Science Approach,
2023
Claremont Graduate University
A New Credit Scoring Model To Reduce Potential Predatory Lending: A Design Science Approach, Anna Zakowska
CGU Theses & Dissertations
This research examines the potential impact of implementing a novel credit scoring model that integrates attributes beyond the traditional FICO model. It aims to address issues related to predatory lending and the financial exclusion affecting individuals often categorized as 'credit invisible,' 'credit unscorable,' 'unbanked,' and 'underbanked.' These individuals typically face difficulties in establishing or repairing a credit history, which poses a challenge for financial institutions in accurately evaluating their creditworthiness. This gap in the credit assessment process often opens doors to unfair lending practices. To tackle this problem, a systematically designed, built, tested, and evaluated innovative credit scoring model was …
Graph Deep Learning Based Hashtag Recommender For Reels On Social Media,
2023
San Jose State University
Graph Deep Learning Based Hashtag Recommender For Reels On Social Media, Sriya Balineni
Master's Projects
Many businesses, including Facebook, Netflix, and YouTube, rely heavily on a recommendation system. Recommendation systems are algorithms that attempt to provide consumers with relevant suggestions for items such as movies, videos, or reels (microvideos) to watch, hashtags for their posts, songs to listen to, and products to purchase. In many businesses, recommender systems are essential because they can generate enormous amounts of revenue and make the platform stand out when compared to others. Reels are a feature of the social media platforms that enable users to create and share videos of up to sixty seconds in length. Individuals, businesses, and …
Wikipedia Web Table Interpretation, Keyword-Based Search, And Ranking,
2023
San Jose State University
Wikipedia Web Table Interpretation, Keyword-Based Search, And Ranking, Kartikee Dabir
Master's Projects
Information retrieval and data interpretation on the web, for the purpose of gaining knowledgeable insights, has been a widely researched topic from the onset of the world wide web or what is today popularly known as the internet. Web tables are structured tabular data present amidst unstructured, heterogenous data on the web. This makes web tables a rich source of information for a variety of tasks like data analysis, data interpretation, and information retrieval pertaining to extracting knowledge from information present on the web. Wikipedia tables which are a subset of web tables hold a huge amount of useful data, …
Nosql Databases In Kubernetes,
2023
San Jose State University
Nosql Databases In Kubernetes, Parth Sandip Mehta
Master's Projects
With the increasing popularity of deploying applications in containers, Kubernetes (K8s) has become one of the most accepted container orchestration systems. Kubernetes helps maintain containers smoothly and simplifies DevOps with powerful automations. It was originally developed as a tool to manage stateless microservices that run seamlessly in containers. The ephemeral nature of pods, the smallest deployable unit, in Kubernetes was well-aligned with stateless applications since destroying and recreating pods didn’t impact applications. There was a need to provision solutions around stateful workloads like databases so as to take advantage of K8s. This project explores this need, the challenges associated and …
Querying The Past: Automatic Source Attribution With Language Models,
2023
Aga Khan University
Querying The Past: Automatic Source Attribution With Language Models, Ryan Muther, Mathew Barber, David Smith
Faculty & Staff Publications
This paper explores new methods for locating the sources used to write a text by 昀椀ne-tuning a variety of language models to rerank candidate sources. These methods promise to shed new light on traditions with complex citational practices, such as in medieval Arabic where citations are ambiguous and boundaries of quotation are poorly defined. After retrieving candidates sources using a baseline BM25 retrieval model, a variety of reranking methods are tested to see how effective they are at the task of source attribution. We conduct experiments on two datasets—English Wikipedia and medieval Arabic historical writing—and employ a variety of retrieval- …
An Empirical Assessment Of The Use Of Password Workarounds And The Cybersecurity Risk Of Data Breaches,
2023
Nova Southeastern University
An Empirical Assessment Of The Use Of Password Workarounds And The Cybersecurity Risk Of Data Breaches, Michael Joseph Rooney
CCAC Theses and Dissertations
Passwords have been used for a long time to grant controlled access to classified spaces, electronics, networks, and more. However, the dramatic increase in user accounts over the past few decades has exposed the realization that technological measures alone cannot ensure a high level of IS security; this leaves the end-users holding a critical role in protecting their organization and personal information. The increased use of IS as a working tool for employees increases the number of accounts and passwords required. Despite being more aware of password entropy, users still often participate in deviant password behaviors, known as ‘password workarounds’ …
Causal Interventional Training For Image Recognition,
2023
Hefei University of Technology
Causal Interventional Training For Image Recognition, Wei Qin, Hanwang Zhang, Richang Hong, Ee-Peng Lim, Qianru Sun
Research Collection School Of Computing and Information Systems
Deep learning models often fit undesired dataset bias in training. In this paper, we formulate the bias using causal inference, which helps us uncover the ever-elusive causalities among the key factors in training, and thus pursue the desired causal effect without the bias. We start from revisiting the process of building a visual recognition system, and then propose a structural causal model (SCM) for the key variables involved in dataset collection and recognition model: object, common sense, bias, context, and label prediction. Based on the SCM, one can observe that there are “good” and “bad” biases. Intuitively, in the image …
