Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Deep learning (2)
- Neural network (2)
- Abstraction refinement (1)
- Area attraction (1)
- CEGAR (1)
-
- Capsule network (1)
- Charitable (1)
- Code learning (1)
- Competition (1)
- Continual learning (1)
- Contrastive pre-training (1)
- Crowdfunding (1)
- Data mining (1)
- Decentralized POMDP (1)
- Diffusion (1)
- Digital economy (1)
- Econometrics (1)
- Externality (1)
- Fast-and-slow learning (1)
- Fundraising (1)
- Fusion Analytics (1)
- GNN (1)
- Generalization (1)
- Hawkes-process (1)
- Homophily (1)
- Inductive (1)
- Interpretability (1)
- Link prediction (1)
- Location-based social network (1)
- Machine Learning (1)
Articles 1 - 10 of 10
Full-Text Articles in Physical Sciences and Mathematics
Generalizing Graph Neural Networks Across Graphs, Time, And Tasks, Zhihao Wen
Generalizing Graph Neural Networks Across Graphs, Time, And Tasks, Zhihao Wen
Dissertations and Theses Collection (Open Access)
Graph-structured data are ubiquitous across numerous real-world contexts, encompassing social networks, commercial graphs, bibliographic networks, and biological systems. Delving into the analysis of these graphs can yield significant understanding pertaining to their corresponding application fields.Graph representation learning offers a potent solution to graph analytics challenges by transforming a graph into a low-dimensional space while preserving its information to the greatest extent possible. This conversion into low-dimensional vectors enables the efficient computation of subsequent graph algorithms. The majority of prior research has concentrated on deriving node representations from a single, static graph. However, numerous real-world situations demand rapid generation of representations …
Continual Learning With Neural Networks, Pham Hong Quang
Continual Learning With Neural Networks, Pham Hong Quang
Dissertations and Theses Collection (Open Access)
Recent years have witnessed tremendous successes of artificial neural networks in many applications, ranging from visual perception to language understanding. However, such achievements have been mostly demonstrated on a large amount of labeled data that is static throughout learning. In contrast, real-world environments are always evolving, where new patterns emerge and the older ones become inactive before reappearing in the future. In this respect, continual learning aims to achieve a higher level of intelligence by learning online on a data stream of several tasks. As it turns out, neural networks are not equipped to learn continually: they lack the ability …
Deepcause: Verifying Neural Networks With Abstraction Refinement, Nguyen Hua Gia Phuc
Deepcause: Verifying Neural Networks With Abstraction Refinement, Nguyen Hua Gia Phuc
Dissertations and Theses Collection (Open Access)
Neural networks have been becoming essential parts in many safety-critical systems (such
as self-driving cars and medical diagnosis). Due to that, it is desirable that neural networks
not only have high accuracy (which traditionally can be validated using a test set) but also
satisfy some safety properties (such as robustness, fairness, or free of backdoor). To verify
neural networks against desired safety properties, there are many approaches developed
based on classical abstract interpretation. However, like in program verification, these
approaches suffer from false alarms, which may hinder the deployment of the networks.
One natural remedy to tackle the problem adopted …
Novel Deep Learning Methods Combined With Static Analysis For Source Code Processing, Duy Quoc Nghi Bui
Novel Deep Learning Methods Combined With Static Analysis For Source Code Processing, Duy Quoc Nghi Bui
Dissertations and Theses Collection (Open Access)
It is desirable to combine machine learning and program analysis so that one can leverage the best of both to increase the performance of software analytics. On one side, machine learning can analyze the source code of thousands of well-written software projects that can uncover patterns that partially characterize software that is reliable, easy to read, and easy to maintain. On the other side, the program analysis can be used to define rigorous and unique rules that are only available in programming languages, which enrich the representation of source code and help the machine learning to capture the patterns better. …
Raising Funds In The Era Of Digital Economy, Deserina Sulaeman
Raising Funds In The Era Of Digital Economy, Deserina Sulaeman
Dissertations and Theses Collection (Open Access)
The rapid advancement in technology and internet penetration have substantially increased the number of economic transactions conducted online. Platforms that connect economic agents play an important role in this digital economy. The unbridled proliferation of digital platforms calls for a closer examination of the factors that could affect the welfare of the increasing number of economic agents who participate in them.
This dissertation examines the factors that could affect the welfare of agents using the setting of a crowdfunding platform where fundraisers develop campaigns to solicit funding from potential donors. These factors can be broadly categorized into three distinct groups: …
Reinforcement Learning For Collective Multi-Agent Decision Making, Duc Thien Nguyen
Reinforcement Learning For Collective Multi-Agent Decision Making, Duc Thien Nguyen
Dissertations and Theses Collection (Open Access)
In this thesis, we study reinforcement learning algorithms to collectively optimize decentralized policy in a large population of autonomous agents. We notice one of the main bottlenecks in large multi-agent system is the size of the joint trajectory of agents which quickly increases with the number of participating agents. Furthermore, the noiseof actions concurrently executed by different agents in a large system makes it difficult for each agent to estimate the value of its own actions, which is well-known as the multi-agent credit assignment problem. We propose a compact representation for multi-agent systems using the aggregate counts to address …
Modeling Movement Decisions In Networks: A Discrete Choice Model Approach, Larry Lin Junjie
Modeling Movement Decisions In Networks: A Discrete Choice Model Approach, Larry Lin Junjie
Dissertations and Theses Collection (Open Access)
In this dissertation, we address the subject of modeling and simulation of agents and their movement decision in a network environment. We emphasize the development of high quality agent-based simulation models as a prerequisite before utilization of the model as an evaluation tool for various recommender systems and policies. To achieve this, we propose a methodological framework for development of agent-based models, combining approaches such as discrete choice models and data-driven modeling.
The discrete choice model is widely used in the field of transportation, with a distinct utility function (e.g., demand or revenue-driven). Through discrete choice models, the movement decision …
Music Popularity, Diffusion And Recommendation In Social Networks: A Fusion Analytics Approach, Jing Ren
Music Popularity, Diffusion And Recommendation In Social Networks: A Fusion Analytics Approach, Jing Ren
Dissertations and Theses Collection (Open Access)
Streaming music and social networks offer an easy way for people to gain access to a massive amount of music, but there are also challenges for the music industry to design for promotion strategies via the new channels. My dissertation employs a fusion of machine-based methods and explanatory empiricism to explore music popularity, diffusion, and promotion in the social network context.
Learning Latent Characteristics Of Locations Using Location-Based Social Networking Data, Thanh Nam Doan
Learning Latent Characteristics Of Locations Using Location-Based Social Networking Data, Thanh Nam Doan
Dissertations and Theses Collection (Open Access)
This dissertation addresses the modeling of latent characteristics of locations to describe the mobility of users of location-based social networking platforms. With many users signing up location-based social networking platforms to share their daily activities, these platforms become a gold mine for researchers to study human visitation behavior and location characteristics. Modeling such visitation behavior and location characteristics can benefit many use- ful applications such as urban planning and location-aware recommender sys- tems. In this dissertation, we focus on modeling two latent characteristics of locations, namely area attraction and neighborhood competition effects using location-based social network data. Our literature survey …
Multi-Cost And Upgradable Spatial Network Databases, Yimin Lin
Multi-Cost And Upgradable Spatial Network Databases, Yimin Lin
Dissertations and Theses Collection (Open Access)
In this dissertation, we first consider data processing problems in multi-cost networks and in upgradable networks. These network types are motivated by real-life situations, which do not fall under the standard spatial network formulation and have not received much attention from database researchers. In a multi-cost network (MCN), each edge is associated with more than one weight type that may affect the user-specific perception of distance. We study two query types on MCNs, namely, the MCN skyline and the MCN top-k query. In an upgradable network, a subset of the edges are amenable to weight reduction, at a cost (e.g., …