Publications

Efficient Graphics Representation with Differentiable Indirection
Sayantan Datta
Carl Marshall
Zhao Dong
Zhengqin Li
D. Nowrouzezahrai
We introduce differentiable indirection – a novel learned primitive that employs differentiable multi-scale lookup tables as an effective … (voir plus)substitute for traditional compute and data operations across the graphics pipeline. We demonstrate its flexibility on a number of graphics tasks, i.e., geometric and image representation, texture mapping, shading, and radiance field representation. In all cases, differentiable indirection seamlessly integrates into existing architectures, trains rapidly, and yields both versatile and efficient results.
2023-12-10
SIGGRAPH Asia 2023 Conference Papers (publié)
doi.org
arxiv.org
Explorable Mesh Deformation Subspaces from Unstructured 3D Generative Models
Arman Maesumi
Paul Guerrero
Noam Aigerman
Vladimir Kim
Matthew Fisher
Siddhartha Chaudhuri
Daniel Ritchie
2023-12-10
SIGGRAPH Asia 2023 Conference Papers (publié)
doi.org
arxiv.org
Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks
MohammadReza Davari
Eugene Belilovsky
2023-12-10
ArXiv (prépublication)
doi.org
arxiv.org
Lagrangian Properties and Control of Soft Robots Modeled with Discrete Cosserat Rods
Lekan Molu
Shaoru Chen
Audrey Sedal
The characteristic ``in-plane"bending associated with soft robots' deformation make them preferred over rigid robots in sophisticated manipu… (voir plus)lation and movement tasks. Executing such motion strategies to precision in soft deformable robots and structures is however fraught with modeling and control challenges given their infinite degrees-of-freedom. Imposing \textit{piecewise constant strains} (PCS) across (discretized) Cosserat microsolids on the continuum material however, their dynamics become amenable to tractable mathematical analysis. While this PCS model handles the characteristic difficult-to-model ``in-plane"bending well, its Lagrangian properties are not exploited for control in literature neither is there a rigorous study on the dynamic performance of multisection deformable materials for ``in-plane"bending that guarantees steady-state convergence. In this sentiment, we first establish the PCS model's structural Lagrangian properties. Second, we exploit these for control on various strain goal states. Third, we benchmark our hypotheses against an Octopus-inspired robot arm under different constant tip loads. These induce non-constant ``in-plane"deformation and we regulate strain states throughout the continuum in these configurations. Our numerical results establish convergence to desired equilibrium throughout the continuum in all of our tests. Within the bounds here set, we conjecture that our methods can find wide adoption in the control of cable- and fluid-driven multisection soft robotic arms; and may be extensible to the (learning-based) control of deformable agents employed in simulated, mixed, or augmented reality.
2023-12-09
ArXiv (prépublication)
doi.org
arxiv.org
Filtering Pixel Latent Variables for Unmixing Noisy and Undersampled Volumetric Images
Catherine Bouchard
Andréanne Deschênes
Vincent Boulanger
Jean-Michel Bellavance
Julia Chabbert
Alexy Pelletier-Rioux
Flavie Lavoie-Cardinal
Christian Gagné
2023-12-07
ArXiv (prépublication)
arxiv.org
arxiv.org
Harnessing Predictive Modeling and Software Analytics in the Age of LLM-Powered Software Development (Invited Talk)
Foutse Khomh
2023-12-07
International Conference on Predictive Models in Software Engineering (publié)
doi.org
Bug Characterization in Machine Learning-based Systems
Mohammad Mehdi Morovati
Amin Nikanjam
Florian Tambon
Foutse Khomh
Z. Jiang
Rapid growth of applying Machine Learning (ML) in different domains, especially in safety-critical areas, increases the need for reliable ML… (voir plus) components, i.e., a software component operating based on ML. Understanding the bugs characteristics and maintenance challenges in ML-based systems can help developers of these systems to identify where to focus maintenance and testing efforts, by giving insights into the most error-prone components, most common bugs, etc. In this paper, we investigate the characteristics of bugs in ML-based software systems and the difference between ML and non-ML bugs from the maintenance viewpoint. We extracted 447,948 GitHub repositories that used one of the three most popular ML frameworks, i.e., TensorFlow, Keras, and PyTorch. After multiple filtering steps, we select the top 300 repositories with the highest number of closed issues. We manually investigate the extracted repositories to exclude non-ML-based systems. Our investigation involved a manual inspection of 386 sampled reported issues in the identified ML-based systems to indicate whether they affect ML components or not. Our analysis shows that nearly half of the real issues reported in ML-based systems are ML bugs, indicating that ML components are more error-prone than non-ML components. Next, we thoroughly examined 109 identified ML bugs to identify their root causes, symptoms, and calculate their required fixing time. The results also revealed that ML bugs have significantly different characteristics compared to non-ML bugs, in terms of the complexity of bug-fixing (number of commits, changed files, and changed lines of code). Based on our results, fixing ML bugs are more costly and ML components are more error-prone, compared to non-ML bugs and non-ML components respectively. Hence, paying a significant attention to the reliability of the ML components is crucial in ML-based systems.
2023-12-04
Empirical Software Engineering (publié)
doi.org
arxiv.org
Deep Neural Networks pruning via the Structured Perspective Regularization
Matteo Cacciola
Antonio Frangioni
Xinlin Li
Andrea Lodi
2023-12-04
SIAM Journal on Mathematics of Data Science (publié)
doi.org
arxiv.org
Towards Causal Representations of Climate Model Data
Julien Boussard
Chandni Nagda
Julia Kaltenborn
Charlotte Emilie Elektra Lange
Philippe Brouillard
Yaniv Gurwicz
Peer Nowack
David Rolnick
Climate models, such as Earth system models (ESMs), are crucial for simulating future climate change based on projected Shared Socioeconomic… (voir plus) Pathways (SSP) greenhouse gas emissions scenarios. While ESMs are sophisticated and invaluable, machine learning-based emulators trained on existing simulation data can project additional climate scenarios much faster and are computationally efficient. However, they often lack generalizability and interpretability. This work delves into the potential of causal representation learning, specifically the \emph{Causal Discovery with Single-parent Decoding} (CDSD) method, which could render climate model emulation efficient \textit{and} interpretable. We evaluate CDSD on multiple climate datasets, focusing on emissions, temperature, and precipitation. Our findings shed light on the challenges, limitations, and promise of using CDSD as a stepping stone towards more interpretable and robust climate model emulation.
2023-12-04
ArXiv (prépublication)
doi.org
arxiv.org
AdaTeacher: Adaptive Multi-Teacher Weighting for Communication Load Forecasting
Chengming Hu
Ju Wang
Di Wu
Yan Xin
Charlie Zhang
Xue Liu
Gregory Dudek
To deal with notorious delays in communication systems, it is crucial to forecast key system characteristics, such as the communication load… (voir plus). Most existing studies aggregate data from multiple edge nodes for improving the forecasting accuracy. However, the bandwidth cost of such data aggregation could be unacceptably high from the perspective of system operators. To achieve both the high forecasting accuracy and bandwidth efficiency, this paper proposes an Adaptive Multi-Teacher Weighting in Teacher-Student Learning approach, namely AdaTeacher, for communication load forecasting of multiple edge nodes. Each edge node trains a local model on its own data. A target node collects multiple models from its neighbor nodes and treats these models as teachers. Then, the target node trains a student model from teachers via Teacher-Student (T-S) learning. Unlike most existing T-S learning approaches that treat teachers evenly, resulting in a limited performance, AdaTeacher introduces a bilevel optimization algorithm to dynamically learn an importance weight for each teacher toward a more effective and accurate T-S learning process. Compared to the state-of-the-art methods, Ada Teacher not only reduces the bandwidth cost by 53.85%, but also improves the load forecasting accuracy by 21.56% and 24.24% on two real-world datasets.
2023-12-03
Global Communications Conference (publié)
doi.org
Energy Saving in Cellular Wireless Networks via Transfer Deep Reinforcement Learning
Di Wu
Yi Tian Xu
M. Jenkin
Seowoo Jang
Ekram Hossain
Xue Liu
Gregory Dudek
With the increasing use of data-intensive mobile applications and the number of mobile users, the demand for wireless data services has been… (voir plus) increasing exponentially in recent years. In order to address this demand, a large number of new cellular base stations are being deployed around the world, leading to a significant increase in energy consumption and greenhouse gas emission. Consequently, energy consumption has emerged as a key concern in the fifth-generation (5G) network era and beyond. Reinforcement learning (RL), which aims to learn a control policy via interacting with the environment, has been shown to be effective in addressing network optimization problems. However, for reinforcement learning, especially deep reinforcement learning, a large number of interactions with the environment are required. This often limits its applicability in the real world. In this work, to better deal with dynamic traffic scenarios and improve real-world applicability, we propose a transfer deep reinforcement learning framework for energy optimization in cellular communication networks. Specifically, we first pre-train a set of RL-based energy-saving policies on source base stations and then transfer the most suitable policy to the given target base station in an unsupervised learning manner. Experimental results demonstrate that base station energy consumption can be reduced significantly using this approach.
2023-12-03
Global Communications Conference (publié)
doi.org
Exhaustive Evaluation of Dynamic Link Prediction
Farimah Poursafaei
Reihaneh Rabbany
Dynamic link prediction is a crucial task in the study of evolving graphs, which serve as abstract models for various real-world application… (voir plus)s. Recent dynamic graph representation learning models have claimed near-perfect performance in this task. However, we argue that the standard evaluation strategy for dynamic link prediction overlooks the sparsity and recurrence patterns inherent in dynamic networks. Specifically, the current strategy suffers from issues such as evaluating models on a balanced set of positive and negative edges, neglecting the reassessment of frequently recurring positive edges, and lacking a comprehensive evaluation of both recurring and new edges.To address these limitations, we propose a novel evaluation strategy called EXHAUSTIVE, which takes into account all relevant negative edges and separately assesses the performance on recurring and new edges. Using our proposed evaluation strategy, we compare the performance of five state-of-the-art dynamic graph learning models on seven benchmark datasets. Compared to the previous common evaluation strategy, we observe an average drop of 62% in Average Precision for dynamic link prediction. Additionally, the ranking of the models also changes under the new evaluation setting. Furthermore, we demonstrate that while all models perform considerably worse when predicting new edges compared to recurring ones, the best performing models differ between the two scenarios. This highlights the importance of employing the proposed evaluation strategy for both the assessment and design of dynamic link prediction models. By adopting our novel evaluation strategy, researchers can obtain a more accurate understanding of model performance in dynamic link prediction, leading to improved evaluation and design of such models.
2023-12-03
2023 IEEE International Conference on Data Mining Workshops (ICDMW) (publié)
doi.org