Computer Sciences Commons^™

Dialogconv: A Lightweight Fully Convolutional Network For Multi-View Response Selection, Yongkang Liu, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang

Research Collection School Of Computing and Information Systems

Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or huge number of parameters. In this paper, we propose a novel lightweight fully convolutional architecture, called DialogConv, for response selection. DialogConv is exclusively built on top of convolution to extract matching features of context and response. Dialogues are modeled in 3D views, where DialogConv performs convolution operations on embedding view, word view and utterance view to capture richer semantic information from multiple contextual views. On the four benchmark datasets, …

A Unified Dialogue User Simulator For Few-Shot Data Augmentation, Dazhen Wan, Zheng Zhang, Qi Zhu, Lizi Liao, Minlie Huang

Research Collection School Of Computing and Information Systems

Pre-trained language models have shown superior performance in task-oriented dialogues. However, existing datasets are on limited scales, which cannot support large-scale pre-training. Fortunately, various data augmentation methods have been developed to augment largescale task-oriented dialogue corpora. However, they heavily rely on annotated data in the target domain, which require a tremendous amount of data collection and human labeling work. In this paper, we build a unified dialogue user simulation model by pre-training on several publicly available datasets. The model can then be tuned on a target domain with fewshot data. The experiments on a target dataset across multiple domains show …

Supply Regulation Under The Exclusion Policy In A Ride-Sourcing Market, Xiaonan Li, Xiangyong Li, Hai Wang, Junxin Shi, Yash P. Aneja

Research Collection School Of Computing and Information Systems

On-demand ride-sourcing platforms have quickly emerged and become ubiquitous in our daily lives. Motivated by the rising public concern about service quality in the ride-sourcing market, this paper aims to examine the impact of exclusion policy that can serve as both quality management and supply regulation strategy. With an exclusion policy, the platform excludes low-quality service providers/drivers from the ride-sourcing market by setting a quality threshold of admission (QTA). We propose a model to describe and analyze the market equilibrium under the exclusion policy and present our analytical and numerical results – some of which are non-intuitive and intriguing. Considering …

On The Robustness Of Diffusion In A Network Under Node Attacks, Alvis Logins, Yuchen Li, Panagiotis Karras

Research Collection School Of Computing and Information Systems

How can we assess a network's ability to maintain its functionality under attacks Network robustness has been studied extensively in the case of deterministic networks. However, applications such as online information diffusion and the behavior of networked public raise a question of robustness in probabilistic networks. We propose three novel robustness measures for networks hosting a diffusion under the Independent Cascade or Linear Threshold model, susceptible to attacks by an adversarial attacker who disables nodes. The outcome of such a process depends on the selection of its initiators, or seeds, by the seeder, as well as on two factors outside …

End-To-End Hierarchical Reinforcement Learning With Integrated Subgoal Discovery, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan, Chai Quek

Research Collection School Of Computing and Information Systems

Hierarchical reinforcement learning (HRL) is a promising approach to perform long-horizon goal-reaching tasks by decomposing the goals into subgoals. In a holistic HRL paradigm, an agent must autonomously discover such subgoals and also learn a hierarchy of policies that uses them to reach the goals. Recently introduced end-to-end HRL methods accomplish this by using the higher-level policy in the hierarchy to directly search the useful subgoals in a continuous subgoal space. However, learning such a policy may be challenging when the subgoal space is large. We propose integrated discovery of salient subgoals (LIDOSS), an end-to-end HRL method with an integrated …

Segment-Wise Time-Varying Dynamic Bayesian Network With Graph Regularization, Xing Yang, Chen Zhang, Baihua Zheng

Research Collection School Of Computing and Information Systems

Time-varying dynamic Bayesian network (TVDBN) is essential for describing time-evolving directed conditional dependence structures in complex multivariate systems. In this article, we construct a TVDBN model, together with a score-based method for its structure learning. The model adopts a vector autoregressive (VAR) model to describe inter-slice and intra-slice relations between variables. By allowing VAR parameters to change segment-wisely over time, the time-varying dynamics of the network structure can be described. Furthermore, considering some external information can provide additional similarity information of variables. Graph Laplacian is further imposed to regularize similar nodes to have similar network structures. The regularized maximum a …

R2f: A General Retrieval, Reading And Fusion Framework For Document-Level Natural Language Inference, Hao Wang, Yixin Cao, Yangguang Li, Zhen Huang, Kun Wang, Jing Shao

Research Collection School Of Computing and Information Systems

Document-level natural language inference (DocNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents. Current datasets and baselines largely follow sentence-level settings, but fail to address the issues raised by longer documents. In this paper, we establish a general solution, named Retrieval, Reading and Fusion (R2F) framework, and a new setting, by analyzing the main challenges of DocNLI: interpretability, long-range dependency, and cross-sentence inference. The basic idea of the framework is to simplify document-level task into a set of sentence-level tasks, and improve both performance and …

Advancing Statistical Learning And Decision Modeling Using Irregularly-Sampled Multivariate Data For Managing Respiratory Diseases, Maryam Alimohammadi

Graduate Theses and Dissertations

Complex healthcare systems require efficient and effective data-driven decision making in various aspects. As patient data becomes more available, advanced statistical learning and machine learning techniques are applied to improve data-driven decision making. However, patient health data, including clinical trial data, medical records, and electronic health records, are associated with several challenges. Patient health data includes medical information of a patient that may includedemographics, information relating to their health or illness, medications and treatments, etc. They are a combination of static and time series variables, with many censoring and missingness in the data, and are irregularly sampled in most cases. …

Learning Generalizable Models For Vehicle Routing Problems Via Knowledge Distillation, Jieyi Bi, Yining Ma, Jiahai Wang, Zhiguang Cao, Jinbiao Chen, Yuan Sun, Yeow Meng Chee

Research Collection School Of Computing and Information Systems

Recent neural methods for vehicle routing problems always train and test the deep models on the same instance distribution (i.e., uniform). To tackle the consequent cross-distribution generalization concerns, we bring the knowledge distillation to this field and propose an Adaptive Multi-Distribution Knowledge Distillation (AMDKD) scheme for learning more generalizable deep models. Particularly, our AMDKD leverages various knowledge from multiple teachers trained on exemplar distributions to yield a light-weight yet generalist student model. Meanwhile, we equip AMDKD with an adaptive strategy that allows the student to concentrate on difficult distributions, so as to absorb hard-to-master knowledge more effectively. Extensive experimental results …

Learning Dynamic Multimodal Implicit And Explicit Networks For Multiple Financial Tasks, Meng Kiat Gary Ang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Many financial f orecasting d eep l earning w orks focus on the single task of predicting stock returns for trading with unimodal numerical inputs. Investment and risk management however involves multiple financial t asks - f orecasts o f expected returns, risks and correlations of multiple stocks in portfolios, as well as important events affecting different stocks - to support decision making. Moreover, stock returns are influenced by large volumes of non-stationary time-series information from a variety of modalities and the propagation of such information across inter-company relationship networks. Such networks could be explicit - observed co-occurrences in online …

What Should Streamers Communicate In Livestream E-Commerce? The Effects Of Social Interactions On Live Streaming Performance, Danyang Song, Xi Chen, Zhiling Guo, Xiao Liu Liu, Ruijin. Jin

Research Collection School Of Computing and Information Systems

Compared with traditional e-commerce, livestreaming e-commerce is characterized by direct and intimate communication between streamers and consumers that stimulates instant social interactions. This study focuses on streamers’ three types of information exchange (i.e., product information, social conversation, and social solicitation) and examines their roles in driving both short-term and long-term livestreaming performance (i.e., sales and customer base growth). We find that the informational role of product information (nonpromotional and promotional) is beneficial not only to sales performance, but also to the growth of the customer base. We also find that social conversation has a relationship-building effect that positively impacts both …

Curiosity-Driven And Victim-Aware Adversarial Policies, Chen Gong, Zhou Yang, Yunpeng Bai, Jieke Shi, Arunesh Sinha, Bowen Xu, David Lo, Xinwen Hou, Guoliang Fan

Research Collection School Of Computing and Information Systems

Recent years have witnessed great potential in applying Deep Reinforcement Learning (DRL) in various challenging applications, such as autonomous driving, nuclear fusion control, complex game playing, etc. However, recently researchers have revealed that deep reinforcement learning models are vulnerable to adversarial attacks: malicious attackers can train adversarial policies to tamper with the observations of a well-trained victim agent, the latter of which fails dramatically when faced with such an attack. Understanding and improving the adversarial robustness of deep reinforcement learning is of great importance in enhancing the quality and reliability of a wide range of DRL-enabled systems. In this paper, …

Beer: Fast O(1/T) Rate For Decentralized Nonconvex Optimization With Communication Compression, Haoyu Zhao, Boyue Li, Zhize Li, Peter Richtarik, Yuejie Chi

Research Collection School Of Computing and Information Systems

Communication efficiency has been widely recognized as the bottleneck for large-scale decentralized machine learning applications in multi-agent or federated environments. To tackle the communication bottleneck, there have been many efforts to design communication-compressed algorithms for decentralized nonconvex optimization, where the clients are only allowed to communicate a small amount of quantized information (aka bits) with their neighbors over a predefined graph topology. Despite significant efforts, the state-of-the-art algorithm in the nonconvex setting still suffers from a slower rate of convergence $O((G/T)^{2/3})$ compared with their uncompressed counterpart, where $G$ measures the data heterogeneity across different clients, and $T$ is the number …

Soteriafl: A Unified Framework For Private Federated Learning With Communication Compression, Zhize Li, Haoyu Zhao, Boyue Li, Yuejie Chi

Research Collection School Of Computing and Information Systems

To enable large-scale machine learning in bandwidth-hungry environments such as wireless networks, significant progress has been made recently in designing communication-efficient federated learning algorithms with the aid of communication compression. On the other end, privacy-preserving, especially at the client level, is another important desideratum that has not been addressed simultaneously in the presence of advanced communication compression techniques yet. In this paper, we propose a unified framework that enhances the communication efficiency of private federated learning with communication compression. Exploiting both general compression operators and local differential privacy, we first examine a simple algorithm that applies compression directly to differentially-private …

Coresets For Vertical Federated Learning: Regularized Linear Regression And K-Means Clustering, Lingxiao Huang, Zhize Li, Jialin Sun, Haoyu Zhao

Research Collection School Of Computing and Information Systems

Vertical federated learning (VFL), where data features are stored in multiple parties distributively, is an important area in machine learning. However, the communication complexity for VFL is typically very high. In this paper, we propose a unified framework by constructing coresets in a distributed fashion for communication-efficient VFL. We study two important learning tasks in the VFL setting: regularized linear regression and $k$-means clustering, and apply our coreset framework to both problems. We theoretically show that using coresets can drastically alleviate the communication complexity, while nearly maintain the solution quality. Numerical experiments are conducted to corroborate our theoretical findings.

On The Merge Of K-Nn Graph, Wan-Lei Zhao, Hui Wang, Peng-Cheng Lin, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

k-nearest neighbor graph is a fundamental data structure in many disciplines such as information retrieval, data-mining, pattern recognition, and machine learning, etc. In the literature, considerable research has been focusing on how to efficiently build an approximate k-nearest neighbor graph (k-NN graph) for a fixed dataset. Unfortunately, a closely related issue of how to merge two existing k-NN graphs has been overlooked. In this paper, we address the issue of k-NN graph merging in two different scenarios. In the first scenario, a symmetric merge algorithm is proposed to combine two approximate k-NN graphs. The algorithm facilitates large-scale processing by the …

Mitigating Popularity Bias In Recommendation With Unbalanced Interactions: A Gradient Perspective, Weijieying Ren, Lei Wang, Kunpeng Liu, Ruocheng Guo, Ee-Peng Lim, Yanjie Fu

Research Collection School Of Computing and Information Systems

Recommender systems learn from historical user-item interactions to identify preferred items for target users. These observed interactions are usually unbalanced following a long-tailed distribution. Such long-tailed data lead to popularity bias to recommend popular but not personalized items to users. We present a gradient perspective to understand two negative impacts of popularity bias in recommendation model optimization: (i) the gradient direction of popular item embeddings is closer to that of positive interactions, and (ii) the magnitude of positive gradient for popular items are much greater than that of unpopular items. To address these issues, we propose a simple yet efficient …

Cold Calls To Enhance Class Participation And Student Engagement, Manoj Thulasidas, Aldy Gunawan

Research Collection School Of Computing and Information Systems

The question whether cold calls increase student engagement in the classroom has not been conclusively answered in the literature. This study describes the automated system to implement unbiased, randomized cold calling by posing a question, allowing all students to think first and then calling on a particular student to respond. Since we already have a measure of the level of student engagement as the self-reported classparticipation entries from the students, its correlation to cold calling is also further studied. The results show that there is a statistically significant increase in the class participation reported, and therefore in student engagement, in …

Conversation Disentanglement With Bi-Level Contrastive Learning, Chengyu Huang, Zheng Zhang, Hao Fei, Lizi Liao

Research Collection School Of Computing and Information Systems

Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations. Existing methods have two main drawbacks. First, they overemphasize pairwise utterance relations but pay inadequate attention to the utterance-to-context relation modeling. Second, a huge amount of human annotated data is required for training, which is expensive to obtain in practice. To address these issues, we propose a general disentangle model based on bi-level contrastive learning. It brings closer utterances in the same session while encourages each utterance to be near its clustered session prototypes in the representation space. Unlike existing approaches, our …

Rural America Is Still Technologically Behind: Why It Matters Now More Than Ever, Paul Force-Emery Mackie

Social Work Department Publications

No abstract provided.

Farmer Adoption Of Advanced Technology In Agribusiness, Justin W. Belcher

USF Tampa Graduate Theses and Dissertations

Normally, family-owned farms are slow to adopt advanced technologies though these technologies can provide several benefits to the farm and have the potential to increase farm production volumes to help meet future population growth. The goal of this study was to document the factors that influence the adoption decision of advanced technologies by family-owned farms and what strategies can be used to motivate adoption. Case study research was conducted to gather data in a more structured way from family-owned farms typically excluded from past research for the purpose of comparing similarities across similar and dissimilar farms. For generalizing similarities, a …

Designing A Messaging Strategy To Improve Information Security Policy Compliance, Federico Giovannetti

USF Tampa Graduate Theses and Dissertations

Lack of employee compliance with information security policies is a key factor driving security incidents. Information security practitioners struggle to enforce policy compliance while employees try to curtail safeguards in favor of expediency and other perceived business goals. Several studies have shown individual and organizational factors influencing this type of employee behavior. However, few have recommended management-level interventions that can be used as a solution framework by information security practitioners.

This research utilized the Design Science Research (DSR) methodology to develop a management-level intervention based on a messaging strategy that aims to help information security practitioners improve the information security …

Redefining Research In Nanotechnology Simulations: A New Approach To Data Caching And Analysis, Darin Tsai, Alan Zhang, Aloysius Rebeiro

The Journal of Purdue Undergraduate Research

No abstract provided.

Mining Product Textual Data For Recommendation Explanations, Le Trung Hoang

Dissertations and Theses Collection (Open Access)

Recommendation explanations help to make sense of recommendations, increasing the likelihood of adoption. Here, we are interested in mining product textual data, an unstructured data type, coming from manufacturers, sellers, or consumers, appearing in many places including title, summary, description, review, question and answers, etc., can be a rich source of information to explain the recommendation. As the explanation task could be decoupled from that of recommendation objective, we can categorize recommendation explanation into integrated approach, that uses a single interpretable model to produce both recommendation and explanation, or pipeline approach, that uses a post-hoc explanation model to produce explanation …

Vlstereoset: A Study Of Stereotypical Bias In Pre-Trained Vision-Language Models, Kankan Zhou, Yibin Lai, Jing Jiang

Research Collection School Of Computing and Information Systems

In this paper we study how to measure stereotypical bias in pre-trained vision-language models. We leverage a recently released text-only dataset, StereoSet, which covers a wide range of stereotypical bias, and extend it into a vision-language probing dataset called VLStereoSet to measure stereotypical bias in vision-language models. We analyze the differences between text and image and propose a probing task that detects bias by evaluating a model’s tendency to pick stereotypical statements as captions for anti-stereotypical images. We further define several metrics to measure both a vision-language model’s overall stereotypical bias and its intra-modal and inter-modal bias. Experiments on six …

What Motivates Software Practitioners To Contribute To Inner Source?, Zhiyuan Wan, Xin Xia, Yun Zhang, David Lo, Daibing Zhou, Qiuyuan Chen, Ahmed E. Hassan

Research Collection School Of Computing and Information Systems

Software development organizations have adopted open source development practices to support or augment their software development processes, a phenomenon referred to as inner source. Given the rapid adoption of inner source, we wonder what motivates software practitioners to contribute to inner source projects. We followed a mixed-methods approach--a qualitative phase of interviews with 20 interviewees, followed by a quantitative phase of an exploratory survey with 124 respondents from 13 countries across four continents. Our study uncovers practitioners' motivation to contribute to inner source projects, as well as how the motivation differs from what motivates practitioners to participate in open source …

Graph Neural Network With Self-Attention And Multi-Task Learning For Credit Default Risk Prediction, Zihao Li, Xianzhi Wang, Lina Yao, Yakun Chen, Guandong Xu, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

We propose a graph neural network with self-attention and multi-task learning (SaM-GNN) to leverage the advantages of deep learning for credit default risk prediction. Our approach incorporates two parallel tasks based on shared intermediate vectors for input vector reconstruction and credit default risk prediction, respectively. To better leverage supervised data, we use self-attention layers for feature representation of categorical and numeric data; we further link raw data into a graph and use a graph convolution module to aggregate similar information and cope with missing values during constructing intermediate vectors. Our method does not heavily rely on feature engineering work and …

Investigating Bloom's Cognitive Skills In Foundation And Advanced Programming Courses From Students' Discussions, Joel Jer Wei Lim, Gottipati Swapna, Kyong Jin Shim

Research Collection School Of Computing and Information Systems

Programming courses provide students with the skills to develop complex business applications. Teaching and learning programming is challenging, and collaborative learning is proposed to help with this challenge. Online discussion forums promote networking with other learners such that they can build knowledge collaboratively. It aids students open their horizons of thought processes to acquire cognitive skills. Cognitive analysis of discussion is critical to understand students' learning process. In this paper, we propose Bloom's taxonomy based cognitive model for programming discussion forums. We present machine learning (ML) based solution to extract students' cognitive skills. Our evaluations on compupting courses show that …

M-Edese: Multi-Domain, Easily Deployable, And Efficiently Searchable Encryption, Jiaming Yuan, Yingjiu Li, Jianting Ning, Robert H. Deng

Research Collection School Of Computing and Information Systems

Searchable encryption is an essential component of cryptography, which allows users to search for keywords and retrieve records from an encrypted database at cloud storage while ensuring the confidentiality of users’ queries. While most existing research on searchable encryption focuses on the single domain setting, we propose the first Multi-Domain, Easily-Deployable, Efficiently-Searchable Encryption (M-EDESE) system that allows users to query keywords cross domains with high efficiency and preserved privacy without additional cooperation from the cloud storage. In the multi-domain setting, a user who belongs to a domain can query keywords from another domain under an inter-domain partnership. Any party can …

Meta-Complementing The Semantics Of Short Texts In Neural Topic Models, Ce Zhang, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Topic models infer latent topic distributions based on observed word co-occurrences in a text corpus. While typically a corpus contains documents of variable lengths, most previous topic models treat documents of different lengths uniformly, assuming that each document is sufficiently informative. However, shorter documents may have only a few word co-occurrences, resulting in inferior topic quality. Some other previous works assume that all documents are short, and leverage external auxiliary data, e.g., pretrained word embeddings and document connectivity. Orthogonal to existing works, we remedy this problem within the corpus itself by proposing a Meta-Complement Topic Model, which improves topic quality …