Publications

ChainBuddy: An AI-assisted Agent System for Helping Users Set up LLM Pipelines
Jingyue Zhang
Ian Arawjo
2024-01-01
UIST (Adjunct Volume) (publié)
doi.org
Common Challenges of Deep Reinforcement Learning Applications Development: An Empirical Study
Mohammad Mehdi Morovati
Florian Tambon
Mina Taraghi
Amin Nikanjam
Foutse Khomh
2024-01-01
Empir. Softw. Eng. (publié)
doi.org
arxiv.org
Connecting Weighted Automata, Tensor Networks and Recurrent Neural Networks through Spectral Learning
Tianyu Li
Doina Precup
Guillaume Rabusseau
2024-01-01
Mach. Learn. (publié)
doi.org
arxiv.org
Consolidating Separate Degradations Model via Weights Fusion and Distillation
Dinesh Daultani
Hugo Larochelle
Real-world images prevalently contain different varieties of degradation, such as motion blur and luminance noise. Computer vision recogniti… (voir plus)on models trained on clean images perform poorly on degraded images. Previously, several works have explored how to perform image classification of degraded images while training a single model for each degradation. Nevertheless, it becomes challenging to host several degradation models for each degradation on limited hardware applications and to estimate degradation parameters correctly at the run-time. This work proposes a method for effectively combining several models trained separately on different degradations into a single model to classify images with different types of degradations. Our proposed method is four-fold: (1) train a base model on clean images, (2) fine-tune the base model in-dividually for all given image degradations, (3) perform a fusion of weights given the fine-tuned models for individual degradations, (4) perform fine-tuning on given task using distillation and cross-entropy loss. Our proposed method can outperform previous state-of-the-art methods of pretraining in out-of-distribution generalization based on degradations such as JPEG compression, salt-and-pepper noise, Gaussian blur, and additive white Gaussian noise by 2.5% on CIFAR-100 dataset and by 1.3% on CIFAR-10 dataset. Moreover, our proposed method can handle degra-dation used for training without any explicit information about degradation at the inference time. Code will be available at https://github.com/dineshdaultani/FusionDistill.
2024-01-01
2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) (publié)
doi.org
Dance of the Neurons: Unraveling Sex from Brain Signals (short paper).
Mohammad-Javad Darvishi Bayazi
Mohammad S. Ghaemi
Jocelyn Faubert
Irina Rish
2024-01-01
ML4CMH@AAAI (publié)
dblp.uni-trier.de
Data-access performance anti-patterns in data-intensive systems
Biruk Asmare Muse
Kawser Wazed Nafi
Foutse Khomh
Giuliano Antoniol
Data-intensive systems handle variable, high volume, and high-velocity data generated by human and digital devices. Like traditional softwar… (voir plus)e, data-intensive systems are prone to technical debts introduced to cope-up with the pressure of time and resource constraints on developers. Data-access is a critical component of data-intensive systems as it determines the overall performance and functionality of such systems. While data access technical debts are getting attention from the research community, technical debts affecting the performance, are not well investigated. Objective: Identify, categorize, and validate data access performance issues in the context of NoSQL-based and polyglot persistence data-intensive systems using qualitative study. Method: We collect issues from NoSQL-based and polyglot persistence open-source data-intensive systems and identify data access performance issues using inductive coding and build a taxonomy of the root causes. Then, we validate the perceived relevance of the newly identified performance issues using a developer survey.
2024-01-01
Empir. Softw. Eng. (publié)
doi.org
arxiv.org
Decoding of Polar Codes Using Quadratic Unconstrained Binary Optimization
Huayi Zhou
Ryan Seah
Marwan Jalaleddine
Warren Gross
2024-01-01
IEEE Journal on Selected Areas in Communications (publié)
doi.org
Deep reinforcement learning for continuous wood drying production line control
François-Alexandre Tremblay
Audrey Durand
Michael Morin
Philippe Marier
Jonathan Gaudreault
2024-01-01
Computers in Industry (publié)
doi.org
In deep reinforcement learning, a pruned network is a good network
Johan Samir Obando Ceron
Aaron Courville
Pablo Samuel Castro
Recent work has shown that deep reinforcement learning agents have difficulty in effectively using their network parameters. We leverage pri… (voir plus)or insights into the advantages of sparse training techniques and demonstrate that gradual magnitude pruning enables agents to maximize parameter effectiveness. This results in networks that yield dramatic performance improvements over traditional networks and exhibit a type of"scaling law", using only a small fraction of the full network parameters.
2024-01-01
ICML (publié)
doi.org
arxiv.org
Dynamic Neural Control Flow Execution: An Agent-Based Deep Equilibrium Approach for Binary Vulnerability Detection
Litao Li
Steven H. H. Ding
Andrew Walenstein
Philippe Charland
Benjamin Fung
2024-01-01
CIKM (publié)
doi.org
arxiv.org
E(3)-Equivariant Mesh Neural Networks
Thuan Nguyen Anh Trang
Khang Nhat Ngo
Daniel Levy
Thieu Vo
Siamak Ravanbakhsh
Truong Son Hy
Triangular meshes are widely used to represent three-dimensional objects. As a result, many recent works have addressed the need for geometr… (voir plus)ic deep learning on 3D meshes. However, we observe that the complexities in many of these architectures do not translate to practical performance, and simple deep models for geometric graphs are competitive in practice. Motivated by this observation, we minimally extend the update equations of E(n)-Equivariant Graph Neural Networks (EGNNs) (Satorras et al., 2021) to incorporate mesh face information and further improve it to account for long-range interactions through a hierarchy. The resulting architecture, Equivariant Mesh Neural Network (EMNN), outperforms other, more complicated equivariant methods on mesh tasks, with a fast run-time and no expensive preprocessing. Our implementation is available at https://github.com/HySonLab/EquiMesh.
2024-01-01
AISTATS (publié)
doi.org
arxiv.org
ECBD: Evidence-Centered Benchmark Design for NLP
Yu Lu Liu
Su Lin Blodgett
Jackie Chi
Jackie Cheung
Kit Cheung
Q. Vera Liao
Alexandra Olteanu
Ziang Xiao
Benchmarking is seen as critical to assessing progress in NLP. However, creating a benchmark involves many design decisions (e.g., which dat… (voir plus)asets to include, which metrics to use) that often rely on tacit, untested assumptions about what the benchmark is intended to measure or is actually measuring. There is currently no principled way of analyzing these decisions and how they impact the validity of the benchmark's measurements. To address this gap, we draw on evidence-centered design in educational assessments and propose Evidence-Centered Benchmark Design (ECBD), a framework which formalizes the benchmark design process into five modules. ECBD specifies the role each module plays in helping practitioners collect evidence about capabilities of interest. Specifically, each module requires benchmark designers to describe, justify, and support benchmark design choices -- e.g., clearly specifying the capabilities the benchmark aims to measure or how evidence about those capabilities is collected from model responses. To demonstrate the use of ECBD, we conduct case studies with three benchmarks: BoolQ, SuperGLUE, and HELM. Our analysis reveals common trends in benchmark design and documentation that could threaten the validity of benchmarks' measurements.
2024-01-01
ACL (1) (publié)
doi.org
arxiv.org