116 citations · 329 across the 40 of their papers we have counts for
43 papers
Algorithmic Simplification of Neural Networks with Mosaic-of-Motifs
Pedram Bakhtiarifard, Tong Chen, Jonathan Wenshøj +2
Large-scale deep learning models are well-suited for compression. Across a variety of tasks, methods like pruning, quantization, and knowledge distillation have been used to achiev…
How Hyper-Datafication Impacts the Sustainability Costs in Frontier AI
Sophia N. Wilson, Sebastian Mair, Mophat Okinyi +3
Large-scale data has fuelled the success of frontier artificial intelligence (AI) models over the past decade. This expansion has relied on sustained efforts by large technology co…
CoDeQ: End-to-End Joint Model Compression with Dead-Zone Quantizer for High-Sparsity and Low-Precision Networks
Jonathan Wenshøj, Tong Chen, Bob Pepin +1
While joint pruning--quantization is theoretically superior to sequential application, current joint methods rely on auxiliary procedures outside the training loop for finding comp…
A Discrepancy-Based Perspective on Dataset Condensation
Tong Chen, Raghavendra Selvan
Given a dataset of finitely many elements , the goal of dataset condensation (DC) is to construct a synthetic dataset $\mathcal{S} = \{\ti…
Performance-Carbon Trade-Offs across Architectural Biases in Shear Flow Forecasting
Sophia N. Wilson, Jens Hesselbjerg Christensen, Raghavendra Selvan
Development of modern deep learning methods has been driven primarily by the push for improving model efficacy (accuracy metrics), leading to large-scale models that require massiv…
Greening AI-enabled Systems with Software Engineering: A Research Agenda for Environmentally Sustainable AI Practices
Luís Cruz, João Paulo Fernandes, Maja H. Kirkeby +22
The environmental impact of Artificial Intelligence (AI)-enabled systems is increasing rapidly, and software engineering plays a critical role in developing sustainable solutions.…
The HCI GenAI CO2ST Calculator: A Tool for Calculating the Carbon Footprint of Generative AI Use in Human-Computer Interaction Research
Nanna Inie, Jeanette Falk, Raghavendra Selvan
Increased usage of generative AI (GenAI) in Human-Computer Interaction (HCI) research induces a climate impact from carbon emissions due to energy consumption of the hardware used…
Position: Neglecting the Sustainability of AI is Fuelling a Global AI Arms Race
Pedram Bakhtiarifard, Pınar Tözün, Christian Igel +1
Sustainability encompasses three key facets: economic, environmental, and social. However, the nascent discourse on sustainable artificial intelligence (AI) predominantly focuses o…
deCIFer: Crystal Structure Prediction from Powder Diffraction Data using Autoregressive Language Models
Frederik Lizak Johansen, Ulrik Friis-Jensen, Erik Bjørnager Dam +3
Novel materials drive advancements in fields ranging from energy storage to electronics, with crystal structure characterization forming a crucial yet challenging step in materials…
Oscillations Make Neural Networks Robust to Quantization
Jonathan Wenshøj, Bob Pepin, Raghavendra Selvan
We challenge the prevailing view that weight oscillations observed during Quantization Aware Training (QAT) are merely undesirable side-effects and argue instead that they are an e…
When Can Memorization Improve Fairness?
Bob Pepin, Christian Igel, Raghavendra Selvan
We study to which extent additive fairness metrics (statistical parity, equal opportunity and equalized odds) can be influenced in a multi-class classification problem by memorizin…
QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge
Hongwei Bran Li, Fernando Navarro, Ivan Ezhov +77
Uncertainty in medical image segmentation tasks, especially inter-rater variability, arising from differences in interpretations and annotations by various experts, presents a sign…
BMRS: Bayesian Model Reduction for Structured Pruning
Dustin Wright, Christian Igel, Raghavendra Selvan
Modern neural networks are often massively overparameterized leading to high compute costs during training and at inference. One effective method to improve both the compute and en…
PePR: Performance Per Resource Unit as a Metric to Promote Small-Scale Deep Learning in Medical Image Analysis
Raghavendra Selvan, Bob Pepin, Christian Igel +2
The recent advances in deep learning (DL) have been accelerated by access to large-scale data and compute. These large-scale resources have been used to train progressively larger…
CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learning
Ulrik Friis-Jensen, Frederik L. Johansen, Andy S. Anker +3
Advances in graph machine learning (ML) have been driven by applications in chemistry as graphs have remained the most expressive representations of molecules. While early graph ML…
Is Adversarial Training with Compressed Datasets Effective?
Tong Chen, Raghavendra Selvan
Dataset Condensation (DC) refers to the recent class of dataset compression methods that generate a smaller, synthetic, dataset from a larger dataset. This synthetic dataset aims t…
Activation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimization
Sebastian Eliassen, Raghavendra Selvan
Efficient training of large-scale graph neural networks (GNNs) has been studied with a specific focus on reducing their memory consumption. Work by Liu et al. (2022) proposed extre…
Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI
Dustin Wright, Christian Igel, Gabrielle Samuel +1
Artificial intelligence (AI) is currently spearheaded by machine learning (ML) methods such as deep learning which have accelerated progress on many tasks thought to be out of reac…
Operating critical machine learning models in resource constrained regimes
Raghavendra Selvan, Julian Schön, Erik B Dam
The accelerated development of machine learning methods, primarily deep learning, are causal to the recent breakthroughs in medical image analysis and computer aided intervention.…
Explicit Temporal Embedding in Deep Generative Latent Models for Longitudinal Medical Image Synthesis
Julian Schön, Raghavendra Selvan, Lotte Nygård +2
Medical imaging plays a vital role in modern diagnostics and treatment. The temporal nature of disease or treatment progression often results in longitudinal data. Due to the cost…
EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search
Pedram Bakhtiarifard, Christian Igel, Raghavendra Selvan
Energy consumption from the selection, training, and deployment of deep learning models has seen a significant uptick recently. This work aims to facilitate the design of energy-ef…
Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image Segmentation
Nicklas Boserup, Raghavendra Selvan
Learning discriminative representations of unlabelled data is a challenging task. Contrastive self-supervised learning provides a framework to learn meaningful representations usin…
Interpreting Latent Spaces of Generative Models for Medical Images using Unsupervised Methods
Julian Schön, Raghavendra Selvan, Jens Petersen
Generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) play an increasingly important role in medical image analysis. The latent space…
Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysis
Raghavendra Selvan, Nikhil Bhagwat, Lasse F. Wolff Anthony +2
The increasing energy consumption and carbon footprint of deep learning (DL) due to growing compute requirements has become a cause of concern. In this work, we focus on the carbon…