• Test-Time Training for Image Inpainting 

  Ghiro, Genseric (University of Waterloo, 2022-06-21)

  Image inpainting is the task of filling missing regions in images with plausible and coherent content. The usual process involves training a CNN on a large collection of examples that it can learn from, to later apply this ...

• Adaptive Cross-Project Bug Localization with Graph Learning 

  Arumugam, Venkatraman (University of Waterloo, 2022-06-07)

  Bug localization is the process of identifying the source code files associated with a bug report. This is important because it allows developers to focus their efforts on fixing the bugs than finding the root cause of ...

• Lox: Protecting the Social Graph in Bridge Distribution 

  Tulloch, Lindsey (University of Waterloo, 2022-05-26)

  Access to the open Internet, free from surveillance and censorship, is an important part of fulfilling the right to privacy. Despite this, in many regions of the world, censorship of the Internet is used to limit access ...

• High-Performance Concurrent Memory Allocation 

  Zulfiqar, Mubeen (University of Waterloo, 2022-05-25)

  Memory management takes a sequence of program-generated allocation/deallocation requests and attempts to satisfy them within a fixed-sized block of memory while minimizing the total amount of memory used. A general-purpose ...

• A Network Integrated Design for Micro-scale Cloud Services 

  Abdel-hadi, Ashraf (University of Waterloo, 2022-05-25)

  We present Falcon, network-integrated scheduler for micro-scale services. Falcon follows a centralized scheduler design to achieve high scheduling efficiency and leverages modern programmable switches to lower the scheduling ...

• All-or-Nothing Private Record Linkage over Streaming Data 

  Premkumar, John Abraham (University of Waterloo, 2022-05-24)

  The prevalence and increasing need for insights obtained from the collection of sensitive data gives rise to the problem of protecting the privacy of this data. The collection and storage of data can be distributed across ...

• Volumetric Weak Supervision for Semantic Segmentation 

  Bashar, Sharhad (University of Waterloo, 2022-05-24)

  Semantic segmentation is a popular task in computer vision. Fully supervised methods are data hungry, they require pixel precise annotations for thousands of images. To reduce user annotation efforts, weak supervision for ...

• Coding Strip: A Tool for Supporting Interplay within Abstraction Ladder for Computational Thinking 

  Suh, Sangho (University of Waterloo, 2022-05-20)

  As technologies advance and play an increasingly larger role in our lives, computational thinking---the ability to understand computing concepts and procedures and their role in the tools we use---has become an important ...

• A Generalized Adversary Method for Quantum Query Complexity 

  Soiffer, Rory (University of Waterloo, 2022-05-20)

  Quantum query complexity measures the minimum number of queries a quantum algorithm needs to make to some input string to compute a function of that input. Query complexity models are widely used throughout quantum computing, ...

• MT-MAG: Accurate and interpretable machine learning for complete or partial taxonomic assignments of metagenome-assembled genomes 

  Wanxin, Li (University of Waterloo, 2022-05-19)

  We propose MT-MAG, a novel machine learning-based software tool for the complete or partial hierarchically-structured taxonomic classification of metagenome-assembled genomes (MAGs). MT-MAG is capable of classifying large ...

• Improved Model Poisoning Attacks and Defenses in Federated Learning with Clustering 

  Li, Xinda (University of Waterloo, 2022-05-12)

  Federated Learning (FL) allows multiple participants to collaboratively train a deep learning model without sharing their private training data. However, due to its distributive nature, FL is vulnerable to various poisoning ...

• A Two-Tier Storage Interface for Low-Latency Kubernetes Deployments 

  Ionita, Teodor Alexandru (University of Waterloo, 2022-05-11)

  Orchestration systems are responsible for automating the management of software deployments on computer systems, managing large numbers of machines. Edge computing is a decentralized compute model describing how compute ...

• Learning Trustworthy Web Sources to Derive Correct Answers and Reduce Health Misinformation in Search 

  Zhang, Dake; Vakili Tahami, Amir; Abualsaud, Mustafa; Smucker, Mark (ACM, 2022-07)

  When searching the web for answers to health questions, people can make incorrect decisions that have a negative effect on their lives if the search results contain misinformation. To reduce health misinformation in search ...

• JITGNN: A Deep Graph Neural Network for Just-In-Time Bug Prediction 

  Keshavarz, Hossein (University of Waterloo, 2022-05-10)

  Just-In-Time (JIT) bug prediction is the problem of predicting software failure immediately after a change is submitted to the code base. JIT bug prediction is often preferred to other types of bug prediction (subsystem, ...

• A conceptual IoT-based early-warning architecture for remote monitoring of COVID-19 patients in wards and at home 

  Paganelli, Antonio Iyda; Velmovitsky, Pedro Elkind; Miranda, Pedro; Branco, Adriano; Alencar, Paulo; Cowan, Donald; Endler, Markus; Morita, Plinio Pelegrini (Elsevier, 2022-05)

  Due to the COVID-19 pandemic, health services around the globe are struggling. An effective system for monitoring patients can improve healthcare delivery by avoiding in-person contacts, enabling early-detection of severe ...

• Faster Algorithms for Sparse Decomposition and Sparse Series Solutions to Differential Equations 

  Lyu, Saiyue (University of Waterloo, 2022-05-09)

  Sparse polynomials are those polynomials with only a few non-zero coefficients relative to their degree. They can appear in practice in polynomial systems as inputs, where the degree of the input sparse polynomial can be ...

• Predicting the Spectrum Quality and Digestive Enzyme for Shotgun Proteomics 

  Gholamizoj, Soroosh (University of Waterloo, 2022-05-03)

  In proteomics, database search programs are routinely used for peptide identification from tandem mass spectrometry data. However, many low-quality spectra cannot be interpreted by any programs. Meanwhile, certain high-quality ...

• Self-supervised Video Representation Learning by Exploiting Video Speed Changes 

  Chen, Lizhe (University of Waterloo, 2022-04-29)

  In recent research, the self-supervised video representation learning methods have achieved improvement by exploring video’s temporal properties, such as playing speeds and temporal order. These works inspire us to exploit ...

• Multi-Resolution and Asymmetric Implementation of Attention in Transformers 

  Chaudhry, Zaid (University of Waterloo, 2022-04-29)

  Transformers are the state-of-the-art for machine translation and grammar error correction. One of the most important components of transformers are the attention layers, but they require significant computational power. ...

• Learning to Rank in the Age of Muppets 

  Hu, Chengcheng (University of Waterloo, 2022-04-26)

  The emergence of BERT in 2018 has brought a huge boon to retrieval effectiveness in many tasks across various domains and led the recent research landscape of IR to transformer-related technologies. While researchers ...

View more