Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
Articles 1 - 13 of 13
Full-Text Articles in Physical Sciences and Mathematics
Generation-Based Code Review Automation: How Far Are We?, Xin Zhou, Kisub Kim, Bowen Xu, Donggyun Han, Junda He, David Lo
Generation-Based Code Review Automation: How Far Are We?, Xin Zhou, Kisub Kim, Bowen Xu, Donggyun Han, Junda He, David Lo
Research Collection School Of Computing and Information Systems
Code review is an effective software quality assurance activity; however, it is labor-intensive and time-consuming. Thus, a number of generation-based automatic code review (ACR) approaches have been proposed recently, which leverage deep learning techniques to automate various activities in the code review process (e.g., code revision generation and review comment generation).We find the previous works carry three main limitations. First, the ACR approaches have been shown to be beneficial in each work, but those methods are not comprehensively compared with each other to show their superiority over their peer ACR approaches. Second, general-purpose pre-trained models such as CodeT5 are proven …
Learning Transferable Perturbations For Image Captioning, Hanjie Wu, Yongtuo Liu, Hongmin Cai, Shengfeng He
Learning Transferable Perturbations For Image Captioning, Hanjie Wu, Yongtuo Liu, Hongmin Cai, Shengfeng He
Research Collection School Of Computing and Information Systems
Present studies have discovered that state-of-the-art deep learning models can be attacked by small but well-designed perturbations. Existing attack algorithms for the image captioning task is time-consuming, and their generated adversarial examples cannot transfer well to other models. To generate adversarial examples faster and stronger, we propose to learn the perturbations by a generative model that is governed by three novel loss functions. Image feature distortion loss is designed to maximize the encoded image feature distance between original images and the corresponding adversarial examples at the image domain, and local-global mismatching loss is introduced to separate the mapping encoding representation …
Coherence And Identity Learning For Arbitrary-Length Face Video Generation, Shuquan Ye, Chu Han, Jiaying Lin, Guoqiang Han, Shengfeng He
Coherence And Identity Learning For Arbitrary-Length Face Video Generation, Shuquan Ye, Chu Han, Jiaying Lin, Guoqiang Han, Shengfeng He
Research Collection School Of Computing and Information Systems
Face synthesis is an interesting yet challenging task in computer vision. It is even much harder to generate a portrait video than a single image. In this paper, we propose a novel video generation framework for synthesizing arbitrary-length face videos without any face exemplar or landmark. To overcome the synthesis ambiguity of face video, we propose a divide-and-conquer strategy to separately address the video face synthesis problem from two aspects, face identity synthesis and rearrangement. To this end, we design a cascaded network which contains three components, Identity-aware GAN (IA-GAN), Face Coherence Network, and Interpolation Network. IA-GAN is proposed to …
Interventional Few-Shot Learning, Zhongqi Yue, Zhang Hanwang, Qianru Sun, Xian-Sheng Hua
Interventional Few-Shot Learning, Zhongqi Yue, Zhang Hanwang, Qianru Sun, Xian-Sheng Hua
Research Collection School Of Computing and Information Systems
We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal Model (SCM) for the causalities among the pre-trained knowledge, sample features, and labels. Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view. It is worth noting that the contribution …
Geoprune: Efficiently Matching Trips In Ride-Sharing Through Geometric Properties, Yixin Xu, Jianzhong Qi, Renata Borovica-Gajic
Geoprune: Efficiently Matching Trips In Ride-Sharing Through Geometric Properties, Yixin Xu, Jianzhong Qi, Renata Borovica-Gajic
Research Collection School Of Computing and Information Systems
On-demand ride-sharing is rapidly growing. Matching trip requests to vehicles efficiently is critical for the service quality of ride-sharing. To match trip requests with vehicles, a prune-And-select scheme is commonly used. The pruning stage identifies feasible vehicles that can satisfy the trip constraints (e.g., trip time). The selection stage selects the optimal one(s) from the feasible vehicles. The pruning stage is crucial to lowering the complexity of the selection stage and to achieve efficient matching. We propose an effective and efficient pruning algorithm called GeoPrune. GeoPrune represents the time constraints of trip requests using circles and ellipses, which can be …
Stochastically Robust Personalized Ranking For Lsh Recommendation Retrieval, Dung D. Le, Hady W. Lauw
Stochastically Robust Personalized Ranking For Lsh Recommendation Retrieval, Dung D. Le, Hady W. Lauw
Research Collection School Of Computing and Information Systems
Locality Sensitive Hashing (LSH) has become one of the most commonly used approximate nearest neighbor search techniques to avoid the prohibitive cost of scanning through all data points. For recommender systems, LSH achieves efficient recommendation retrieval by encoding user and item vectors into binary hash codes, reducing the cost of exhaustively examining all the item vectors to identify the topk items. However, conventional matrix factorization models may suffer from performance degeneration caused by randomly-drawn LSH hash functions, directly affecting the ultimate quality of the recommendations. In this paper, we propose a framework named SRPR, which factors in the stochasticity of …
Interpretable Rumor Detection In Microblogs By Attending To User Interactions, Ling Min Serena Khoo, Hai Leong Chieu, Zhong Qian, Jing Jiang
Interpretable Rumor Detection In Microblogs By Attending To User Interactions, Ling Min Serena Khoo, Hai Leong Chieu, Zhong Qian, Jing Jiang
Research Collection School Of Computing and Information Systems
We address rumor detection by learning to differentiate between the community’s response to real and fake claims in microblogs. Existing state-of-the-art models are based on tree models that model conversational trees. However, in social media, a user posting a reply might be replying to the entire thread rather than to a specific user. We propose a post-level attention model (PLAN) to model long distance interactions between tweets with the multi-head attention mechanism in a transformer network. We investigated variants of this model: (1) a structure aware self-attention model (StA-PLAN) that incorporates tree structure information in the transformer network, and (2) …
Coupled Rain Streak And Background Estimation Via Separable Element-Wise Attention, Yinjie Tan, Qiang Wen, Jing Qin, Jianbo Jiao, Guoqiang Han, Shengfeng He
Coupled Rain Streak And Background Estimation Via Separable Element-Wise Attention, Yinjie Tan, Qiang Wen, Jing Qin, Jianbo Jiao, Guoqiang Han, Shengfeng He
Research Collection School Of Computing and Information Systems
Single image de-raining is challenging especially in the scenarios with dense rain streaks. Existing methods resolve this problem by predicting the rain streaks of the image, which constrains the network to focus on local rain streaks features. However, dense rain streaks are visually similar to mist or fog (with large intensities), in this case, the training objective should be shifted to image recovery instead of extracting rain streaks. In this paper, we propose a coupled rain streak and background estimation network that explores the intrinsic relations between two tasks. In particular, our network produces task-dependent feature maps, each part of …
Visualizing The Invisible: Occluded Vehicle Segmentation And Recovery, Xiaosheng Yan, Feigege Wang, Wenxi Liu, Yuanlong Yu, Shengfeng He, Jia Pan
Visualizing The Invisible: Occluded Vehicle Segmentation And Recovery, Xiaosheng Yan, Feigege Wang, Wenxi Liu, Yuanlong Yu, Shengfeng He, Jia Pan
Research Collection School Of Computing and Information Systems
In this paper, we propose a novel iterative multi-task framework to complete the segmentation mask of an occluded vehicle and recover the appearance of its invisible parts. In particular, firstly, to improve the quality of the segmentation completion, we present two coupled discriminators that introduce an auxiliary 3D model pool for sampling authentic silhouettes as adversarial samples. In addition, we propose a two-path structure with a shared network to enhance the appearance recovery capability. By iteratively performing the segmentation completion and the appearance recovery, the results will be progressively refined. To evaluate our method, we present a dataset, Occluded Vehicle …
Robust Factorization Machine: A Doubly Capped Norms Minimization, Chenghao Liu, Teng Zhang, Jundong Li, Jianwen Yin, Peilin Zhao, Jianling Sun, Steven C. H. Hoi
Robust Factorization Machine: A Doubly Capped Norms Minimization, Chenghao Liu, Teng Zhang, Jundong Li, Jianwen Yin, Peilin Zhao, Jianling Sun, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
Factorization Machine (FM) is a general supervised learning framework for many AI applications due to its powerful capability of feature engineering. Despite being extensively studied, existing FM methods have several limitations in common. First of all, most existing FM methods often adopt the squared loss in the modeling process, which can be very sensitive when the data for learning contains noises and outliers. Second, some recent FM variants often explore the low-rank structure of the feature interactions matrix by relaxing the low-rank minimization problem as a trace norm minimization, which cannot always achieve a tight approximation to the original one. …
Discovering Hidden Topical Hubs And Authorities In Online Social Networks, Roy Ka-Wei Lee, Tuan-Anh Hoang, Ee-Peng Lim
Discovering Hidden Topical Hubs And Authorities In Online Social Networks, Roy Ka-Wei Lee, Tuan-Anh Hoang, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
Finding influential users in online social networks is an important problem with many possible useful applications. HITS and other link analysis methods, in particular, have been often used to identify hub and authority users in web graphs and online social networks. These works, however, have not considered topical aspect of links in their analysis. A straightforward approach to overcome this limitation is to first apply topic models to learn the user topics before applying the HITS algorithm. In this paper, we instead propose a novel topic model known as Hub and Authority Topic (HAT) model to combines the two process …
Finding All Nearest Neighbors With A Single Graph Traversal, Yixin Xu, Qi Jianzhong, Borovica‐Gajic Renata, Kulik Lars
Finding All Nearest Neighbors With A Single Graph Traversal, Yixin Xu, Qi Jianzhong, Borovica‐Gajic Renata, Kulik Lars
Research Collection School Of Computing and Information Systems
Finding the nearest neighbor is a key operation in data analysis and mining. An important variant of nearest neighbor query is the all nearest neighbor (ANN) query, which reports all nearest neighbors for a given set of query objects. Existing studies on ANN queries have focused on Euclidean space. Given the widespread occurrence of spatial networks in urban environments, we study the ANN query in spatial network settings. An example of an ANN query on spatial networks is finding the nearest car parks for all cars currently on the road. We propose VIVET, an index-based algorithm to efficiently process ANN …
Pairwise Relation Classification With Mirror Instances And A Combined Convolutional Neural Network, Jianfei Yu, Jing Jiang
Pairwise Relation Classification With Mirror Instances And A Combined Convolutional Neural Network, Jianfei Yu, Jing Jiang
Research Collection School Of Computing and Information Systems
Relation classification is the task of classifying the semantic relations between entity pairs in text. Observing that existing work has not fully explored using different representations for relation instances, especially in order to better handle the asymmetry of relation types, in this paper, we propose a neural network based method for relation classification that combines the raw sequence and the shortest dependency path representations of relation instances and uses mirror instances to perform pairwise relation classification. We evaluate our proposed models on two widely used datasets: SemEval-2010 Task 8 and ACE-2005. The empirical results show that our combined model together …