Vlstereoset: A Study Of Stereotypical Bias In Pre-Trained Vision-Language Models,
2022
Singapore Management University
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 …
M-Edese: Multi-Domain, Easily Deployable, And Efficiently Searchable Encryption,
2022
Singapore Management University
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 …
What Motivates Software Practitioners To Contribute To Inner Source?,
2022
Singapore Management University
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,
2022
University of Technology Sydney
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 …
Delving Deep Into Pixelized Face Recovery And Defense,
2022
Singapore Management University
Delving Deep Into Pixelized Face Recovery And Defense, Zhixuan Zhong, Yong Du, Yang Zhou, Jiangzhong Cao, Shengfeng He
Research Collection School Of Computing and Information Systems
Pixelization is arguably one of the most well-adopted deterministic obfuscation techniques for privacy preservation purposes. Although the recovery of pixelized faces is underexplored, the powerful deep neural networks might combat this problem in a data-driven manner. As a consequence, an unbreakable pixelization approach is desired. To achieve this goal, in this paper, we delve into two contradictory problems of unrecoverable pixelization and its counterpart, depixelization, by leveraging the best recovery to strengthen the robustness of the unrecoverable pixelized patterns. In particular, on the offensive end of recovery, we combat the large and continuous nature of pixelized regions by proposing two …
Photovoltaic Cells For Energy Harvesting And Indoor Positioning,
2022
Singapore Management University
Photovoltaic Cells For Energy Harvesting And Indoor Positioning, Hamada Rizk, Dong Ma, Mahbub Hassan, Moustafa Youssef
Research Collection School Of Computing and Information Systems
We propose SoLoc, a lightweight probabilistic fingerprinting-based technique for energy-free device-free indoor localization. The system harnesses photovoltaic currents harvested by the photovoltaic cells in smart environments for simultaneously powering digital devices and user positioning. The basic principle is that the location of the human interferes with the lighting received by the photovoltaic cells, thus producing a location fingerprint on the generated photocurrents. To ensure resilience to noisy measurements, SoLoc constructs probability distributions as a photovoltaic fingerprint at each location. Then, we employ a probabilistic graphical model for estimating the user location in the continuous space. Results show that SoLoc can …
Investigating Bloom's Cognitive Skills In Foundation And Advanced Programming Courses From Students' Discussions,
2022
Singapore Management University
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 …
Codematcher: A Tool For Large-Scale Code Search Based On Query Semantics Matching,
2022
Chongqing University
Codematcher: A Tool For Large-Scale Code Search Based On Query Semantics Matching, Chao Liu, Xuanlin Bao, Xin Xia, Meng Yan, David Lo, Ting Zhang
Research Collection School Of Computing and Information Systems
Due to the emergence of large-scale codebases, such as GitHub and Gitee, searching and reusing existing code can help developers substantially improve software development productivity. Over the years, many code search tools have been developed. Early tools leveraged the information retrieval (IR) technique to perform an efficient code search for a frequently changed large-scale codebase. However, the search accuracy was low due to the semantic mismatch between query and code. In the recent years, many tools leveraged Deep Learning (DL) technique to address this issue. But the DL-based tools are slow and the search accuracy is unstable.In this paper, we …
Artificial Intelligence For Natural Disaster Management,
2022
Singapore Management University
Artificial Intelligence For Natural Disaster Management, Guansong Pang
Research Collection School Of Computing and Information Systems
Artificial intelligence (AI) can leverage massive amount of diverse types of data, such as geospatial data, social media data, and wireless network sensor data, to enhance our understanding of natural disasters, their forecasting and detection, and humanitarian assistance in natural disaster management (NDM). Due to this potential, different communities have been dedicating enormous efforts to the development and/or adoption of AI technologies for NDM. This article provides an overview of these efforts and discusses major challenges and opportunities in this topic.
A Fine-Grained Data Set And Analysis Of Tangling In Bug Fixing Commits,
2022
Singapore Management University
A Fine-Grained Data Set And Analysis Of Tangling In Bug Fixing Commits, Steffen Herbold, Alexander Trautsch, Benjamin Ledel, Alireza Aghamohammadi, Taher Ahmed Ghaleb, Kuljit Kaur Chahal, Tim Bossenmaier, Bhaveet Nagaria, Philip Makedonski, Matin Nili Ahmadabadi, Kristóf Szabados, Helge Spieker, Matej Madeja, Nathaniel G. Hoy, Christoph Treude, Shangwen Wang, Gema Rodríguez-Pérez, Ricardo Colomo-Palacios, Roberto Verdecchia, Paramvir Singh
Research Collection School Of Computing and Information Systems
Context: Tangled commits are changes to software that address multiple concerns at once. For researchers interested in bugs, tangled commits mean that they actually study not only bugs, but also other concerns irrelevant for the study of bugs.Objective: We want to improve our understanding of the prevalence of tangling and the types of changes that are tangled within bug fixing commits.Methods: We use a crowd sourcing approach for manual labeling to validate which changes contribute to bug fixes for each line in bug fixing commits. Each line is labeled by four participants. If at least three participants agree on the …
The Necessity Of Cloud-Based Simulator For Indonesia's Maritime Education And Training Institutions,
2022
World Maritime University
The Necessity Of Cloud-Based Simulator For Indonesia's Maritime Education And Training Institutions, Stevian Geerbel Adrianes Rakka
World Maritime University Dissertations
No abstract provided.
Text Mining Policy Documents To Support Transboundary Integrated Ecosystem Assessment : The Case Of The South Mid-Atlantic Ridge,
2022
World Maritime University
Text Mining Policy Documents To Support Transboundary Integrated Ecosystem Assessment : The Case Of The South Mid-Atlantic Ridge, Debora Cristina Ferrari Ramalho
World Maritime University Dissertations
No abstract provided.
Data Sharing Through Open Access Data Repositories,
2022
Kennesaw State University
Data Sharing Through Open Access Data Repositories, Karin Bennedsen
All Things Open
The National Institutes of Health has expanded their data sharing requirements for obtaining funding to now include all awards for research producing scientific data to accelerate “biomedical research discovery, in part, by enabling validation of research results, providing accessibility to high-value datasets, and promoting data reuse for future research studies.” The new policy requiring a Data Management & Sharing Plan (DMSP) for all applications goes into effect January 25th, 2023. A DMSP includes where the data will be stored. This lightning talk will review Open Access Data Repositories. Don’t let the task of trying to find data storage hold you …
Tgdm: Target Guided Dynamic Mixup For Cross-Domain Few-Shot Learning,
2022
Singapore Management University
Tgdm: Target Guided Dynamic Mixup For Cross-Domain Few-Shot Learning, Linhai Zhuo, Yuqian Fu, Jingjing Chen, Yixin Cao, Yu-Gang Jiang
Research Collection School Of Computing and Information Systems
Given sufficient training data on the source domain, cross-domain few-shot learning (CD-FSL) aims at recognizing new classes with a small number of labeled examples on the target domain. The key to addressing CD-FSL is to narrow the domain gap and transferring knowledge of a network trained on the source domain to the target domain. To help knowledge transfer, this paper introduces an intermediate domain generated by mixing images in the source and the target domain. Specifically, to generate the optimal intermediate domain for different target data, we propose a novel target guided dynamic mixup (TGDM) framework that leverages the target …
Hierarchical Hourglass Convolutional Network For Efficient Video Classification,
2022
[email protected]
Hierarchical Hourglass Convolutional Network For Efficient Video Classification, Yi Tan, Yanbin Hao, Hao Zhang, Shuo Wang
PhD Student’s Publications Collection
Videos naturally contain dynamic variation over the temporal axis, which will result in the same visual clues (e.g., semantics, objects) changing their scale, position, and perspective patterns between adjacent frames. A primary trend in video CNN is adopting spatial-2D convolution for spatial semantics and temporal-1D convolution for temporal dynamics. Though the direction achieves a favorable balance between efficiency and efficacy, it suffers from misalignment of visual clues with large displacements. Particularly, rigid temporal convolution would fail to capture correct motions when a specific target moves out of the reception field of temporal convolution between adjacent frames.To tackle large visual displacements …
Adaptive Structural Similarity Preserving For Unsupervised Cross Modal Hashing,
2022
Singapore Management University
Adaptive Structural Similarity Preserving For Unsupervised Cross Modal Hashing, Liang Li, Baihua Zheng, Weiwei Sun
Research Collection School Of Computing and Information Systems
Relation Extraction (RE) is a vital step to complete Knowledge Graph (KG) by extracting entity relations from texts. However, it usually suffers from the long-tail issue. The training data mainly concentrates on a few types of relations, leading to the lack of sufficient annotations for the remaining types of relations. In this paper, we propose a general approach to learn relation prototypes from unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient training data. We learn relation prototypes as an implicit factor between entities, which reflects the meanings of relations as well …
Interactive Contrastive Learning For Self-Supervised Entity Alignment,
2022
Singapore Management University
Interactive Contrastive Learning For Self-Supervised Entity Alignment, Kaisheng Zeng, Zhenhao Dong, Lei Hou, Yixin Cao, Minghao Hu, Jifan Yu, Xin Lv, Lei Cao, Xin Wang, Haozhuang Liu, Yi Huang, Jing Wan, Juanzi Li
Research Collection School Of Computing and Information Systems
Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without the use of pre-aligned entity pairs. The current state-of-the-art (SOTA) selfsupervised EA approach draws inspiration from contrastive learning, originally designed in computer vision based on instance discrimination and contrastive loss, and suffers from two shortcomings. Firstly, it puts unidirectional emphasis on pushing sampled negative entities far away rather than pulling positively aligned pairs close, as is done in the well-established supervised EA. Secondly, it advocates the minimum information requirement for self-supervised EA, while we argue that self-described KG’s side information (e.g., entity name, relation name, …
Ergo: Event Relational Graph Transformer For Document-Level Event Causality Identification,
2022
Singapore Management University
Ergo: Event Relational Graph Transformer For Document-Level Event Causality Identification, Meiqi Chen, Yixin Cao, Kunquan Deng, Mukai Li, Kun Wang, Jing Shao, Yan Zhang
Research Collection School Of Computing and Information Systems
Document-level Event Causality Identification (DECI) aims to identify event-event causal relations in a document. Existing works usually build an event graph for global reasoning across multiple sentences. However, the edges between events have to be carefully designed through heuristic rules or external tools. In this paper, we propose a novel Event Relational Graph TransfOrmer (ERGO) framework1 for DECI, to ease the graph construction and improve it over the noisy edge issue. Different from conventional event graphs, we define a pair of events as a node and build a complete event relational graph without any prior knowledge or tools. This naturally …
On Mitigating Hard Clusters For Face Clustering,
2022
Singapore Management University
On Mitigating Hard Clusters For Face Clustering, Yingjie Chen, Huasong Zhong, Chong Chen, Chen Shen, Jianqiang Huang, Tao Wang, Yun Liang, Qianru Sun
Research Collection School Of Computing and Information Systems
Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. It remains challenging to identify small or sparse face image clusters that we call hard clusters, which is caused by the heterogeneity, i.e., high variations in size and sparsity, of the clusters. Consequently, the conventional way of using a uniform threshold (to identify clusters) often leads to a terrible misclassification for the samples that should belong to hard clusters. We tackle this problem by leveraging the neighborhood information of samples and inferring the cluster memberships (of samples) in a probabilistic way. We introduce …
Ngram-Oaxe: Phrase-Based Order-Agnostic Cross Entropy For Non-Autoregressive Machine Translation,
2022
Singapore Management University
Ngram-Oaxe: Phrase-Based Order-Agnostic Cross Entropy For Non-Autoregressive Machine Translation, Cunxiao Du, Zhaopeng Tu, Longyue Wang, Jing Jiang
Research Collection School Of Computing and Information Systems
Recently, a new training oaxe loss has proven effective to ameliorate the effect of multimodality for non-autoregressive translation (NAT), which removes the penalty of word order errors in the standard cross-entropy loss. Starting from the intuition that reordering generally occurs between phrases, we extend oaxe by only allowing reordering between ngram phrases and still requiring a strict match of word order within the phrases. Extensive experiments on NAT benchmarks across language pairs and data scales demonstrate the effectiveness and universality of our approach. Further analyses show that ngram noaxe indeed improves the translation of ngram phrases, and produces more fluent …
