Publications

Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models
Vikram Voleti
Christopher Pal
Adam Oberman
Generative models based on denoising diffusion techniques have led to an unprecedented increase in the quality and diversity of imagery that… (see more) is now possible to create with neural generative models. However, most contemporary state-of-the-art methods are derived from a standard isotropic Gaussian formulation. In this work we examine the situation where non-isotropic Gaussian distributions are used. We present the key mathematical derivations for creating denoising diffusion models using an underlying non-isotropic Gaussian noise model. We also provide initial experiments with the CIFAR10 dataset to help verify empirically that this more general modelling approach can also yield high-quality samples.
2022-11-28
NeurIPS.cc/2022/Workshop/SBM (poster)
doi.org
openreview.net
Continual Learning with Foundation Models: An Empirical Study of Latent Replay
Oleksiy Ostapenko
Timothee LESORT
Pau Rodríguez
Md Rifat Arefin
Arthur Douillard
Irina Rish
Laurent Charlin
Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of… (see more) downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models as a foundation for downstream continual learning (CL) scenarios. Our goal is twofold. First, we want to understand the compute-accuracy trade-off between CL in the raw-data space and in the latent space of pre-trained encoders. Second, we investigate how the characteristics of the encoder, the pre-training algorithm and data, as well as of the resulting latent space affect CL performance. For this, we compare the efficacy of various pre-trained models in large-scale benchmarking scenarios with a vanilla replay setting applied in the latent and in the raw-data space. Notably, this study shows how transfer, forgetting, task similarity and learning are dependent on the input data characteristics and not necessarily on the CL algorithms. First, we show that under some circumstances reasonable CL performance can readily be achieved with a non-parametric classifier at negligible compute. We then show how models pre-trained on broader data result in better performance for various replay sizes. We explain this with representational similarity and transfer properties of these representations. Finally, we show the effectiveness of self-supervised pre-training for downstream domains that are out-of-distribution as compared to the pre-training domain. We point out and validate several research directions that can further increase the efficacy of latent CL including representation ensembling. The diverse set of datasets used in this study can serve as a compute-efficient playground for further CL research. The codebase is available under https://github.com/oleksost/latent_CL.
2022-11-27
Proceedings of The 1st Conference on Lifelong Learning Agents (published)
doi.org
proceedings.mlr.press
Improving Meta-Learning Generalization with Activation-Based Early-Stopping
Simon Guiroy
Christopher Pal
Goncalo Mordido
A. Chandar
2022-11-27
Proceedings of The 1st Conference on Lifelong Learning Agents (published)
doi.org
proceedings.mlr.press
Pitfalls of Conditional Batch Normalization for Contextual Multi-Modal Learning
Ivaxi Sheth
Aamer Abdul Rahman
Mohammad Havaei
S Ebrahimi Kahou
Humans have perfected the art of learning from multiple modalities through sensory organs. Despite their impressive predictive performance o… (see more)n a single modality, neural networks cannot reach human level accuracy with respect to multiple modalities. This is a particularly challenging task due to variations in the structure of respective modalities. Conditional Batch Normalization (CBN) is a popular method that was proposed to learn contextual features to aid deep learning tasks. This technique uses auxiliary data to improve representational power by learning affine transformations for convolutional neural networks. Despite the boost in performance observed by using CBN layers, our work reveals that the visual features learned by introducing auxiliary data via CBN deteriorates. We perform comprehensive experiments to evaluate the brittleness of CBN networks to various datasets, suggesting that learning from visual features alone could often be superior for generalization. We evaluate CBN models on natural images for bird classification and histology images for cancer type classification. We observe that the CBN network learns close to no visual features on the bird classification dataset and partial visual features on the histology dataset. Our extensive experiments reveal that CBN may encourage shortcut learning between the auxiliary data and labels.
2022-11-27
ArXiv (preprint)
doi.org
arxiv.org
Shimming toolbox: An open‐source software toolbox for <scp>B0</scp> and <scp>B1</scp> shimming in MRI
Alexandre D'Astous
Gaspard Cereza
Daniel Papp
Kyle M. Gilbert
Jason P. Stockmann
Eva Alonso‐Ortiz
Julien Cohen‐Adad
Introduce Shimming Toolbox ( https://shimming‐toolbox.org), an open‐source software package for prototyping new methods and performing s… (see more)tatic, dynamic, and real‐time B0 shimming as well as B1 shimming experiments. Shimming Toolbox features various field mapping techniques, manual and automatic masking for the brain and spinal cord, B0 and B1 shimming capabilities accessible through a user‐friendly graphical user interface. Validation of Shimming Toolbox was demonstrated in three scenarios: (i) B0 dynamic shimming in the brain at 7T using custom AC/DC coils, (ii) B0 real‐time shimming in the spinal cord at 3T, and (iii) B1 static shimming in the spinal cord at 7T. Shimming Toolbox provides an open‐source platform where researchers can collaborate, prototype and conveniently test B0 and B1 shimming experiments. Future versions will include additional field map preprocessing techniques, optimization algorithms, and compatibility across multiple MRI manufacturers.
2022-11-27
Magnetic Resonance in Medicine (unknown)
doi.org
Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance
Mats Leon Richter
Christopher Pal
Minimal changes to neural architectures (e.g. changing a single hyperparameter in a key layer), can lead to significant gains in predictive … (see more)performance in Convolutional Neural Networks (CNNs). In this work, we present a new approach to receptive field analysis that can yield these types of theoretical and empirical performance gains across twenty well-known CNN architectures examined in our experiments. By further developing and formalizing the analysis of receptive field expansion in convolutional neural networks, we can predict unproductive layers in an automated manner before ever training a model. This allows us to optimize the parameter-efficiency of a given architecture at low cost. Our method is computationally simple and can be done in an automated manner or even manually with minimal effort for most common architectures. We demonstrate the effectiveness of this approach by increasing parameter efficiency across past and current top-performing CNN-architectures. Specifically, our approach is able to improve ImageNet1K performance across a wide range of well-known, state-of-the-art (SOTA) model classes, including: VGG Nets, MobileNetV1, MobileNetV3, NASNet A (mobile), MnasNet, EfficientNet, and ConvNeXt - leading to a new SOTA result for each model class.
2022-11-25
ArXiv (preprint)
doi.org
arxiv.org
Applied artificial intelligence in healthcare: Listening to the winds of change in a post-COVID-19 world
Arash Shaban-Nejad
Martin Michalowski
Simone Bianco
John S. Brownstein
David L Buckeridge
Robert L Davis
2022-11-24
Experimental Biology and Medicine (published)
doi.org
Beyond Mahalanobis-Based Scores for Textual OOD Detection
Pierre Colombo
Eduardo D. C. Gomes
Guillaume Staerman
Nathan Noiry
Pablo Piantanida
2022-11-23
ArXiv (preprint)
doi.org
openreview.net
Towards Adaptive Cybersecurity for Green IoT
Talal Halabi
Martine Bellaiche
Benjamin C. M. Fung
The Internet of Things (IoT) paradigm has led to an explosion in the number of IoT devices and an exponential rise in carbon footprint incur… (see more)red by overburdened IoT networks and pervasive cloud/edge communications. Hence, there is a growing interest in industry and academia to enable the efficient use of computing infrastructures by optimizing the management of data center and IoT resources (hardware, software, network, and data) and reducing operational costs to slash greenhouse gas emissions and create healthy environments. Cybersecurity has also been considered in such efforts as a contributor to these environmental issues. Nonetheless, most green security approaches focus on designing low-overhead encryption schemes and do not emphasize energy-efficient security from architectural and deployment viewpoints. This paper sheds light on the emerging paradigm of adaptive cybersecurity as one of the research directions to support sustainable computing in green IoT. It presents three potential research directions and their associated methods for designing and deploying adaptive security in green computing and resource-constrained IoT environments to save on energy consumption. Such efforts will transform the development of data-driven IoT security solutions to be greener and more environment-friendly.
2022-11-23
2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS) (published)
doi.org
Age differences in functional brain networks associated with loneliness and empathy
Laetitia Mwilambwe-Tshilobo
Roni Setton
Danilo Bzdok
Gary R. Turner
R. Nathan Spreng
Network Neuroscience
Loneliness is associated with differences in resting-state functional connectivity (RSFC) within and between large-scale networks in early- … (see more)and middle-aged adult cohorts. However, age-related changes in associations between sociality and brain function into late adulthood are not well understood. Here, we examined age differences in the association between two dimensions of sociality—loneliness and empathic responding—and RSFC of the cerebral cortex. Self-report measures of loneliness and empathy were inversely related across the entire sample of younger (mean age = 22.6y, n = 128) and older (mean age = 69.0y, n = 92) adults. Using multivariate analyses of multi-echo fMRI RSFC, we identified distinct functional connectivity patterns for individual and age group differences associated with loneliness and empathic responding. Loneliness in young and empathy in both age groups was related to greater visual network integration with association networks (e.g., default, fronto-parietal control). In contrast, loneliness was positively related to within- and between-network integration of association networks for older adults. These results extend our previous findings in early- and middle-aged cohorts, demonstrating that brain systems associated with loneliness, as well as empathy, differ in older age. Further, the findings suggest that these two aspects of social experience engage different neurocognitive processes across human life-span development.
2022-11-22
Network Neuroscience (published)
doi.org
Momentum Extragradient is Optimal for Games with Cross-Shaped Spectrum
Junhyung Lyle Kim
Gauthier Gidel
Anastasios Kyrillidis
Fabian Pedregosa
Google Research
© J.l. Kim
The extragradient method has recently gained a lot of attention, due to its convergence behavior on smooth games. In games, the eigenvalues … (see more)of the Jacobian of the vector field are distributed on the complex plane, exhibiting more convoluted dynamics compared to minimization. In this work, we take a polynomial-based analysis of the extragradient with momentum for optimizing games with \emph{cross-shaped} spectrum on the complex plane. We show two results: first, the extragradient with momentum exhibits three different modes of convergence based on the hyperparameter setup: when the eigenvalues are distributed
2022-11-22
NeurIPS.cc/2022/Workshop/OPT (poster)
openreview.net
openreview.net
Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
Sitao Luan
Harry Zhao
Mingde Zhao
Chenqing Hua
Xiao-Wen Chang
Doina Precup
The core operation of current Graph Neural Networks (GNNs) is the aggregation enabled by the graph Laplacian or message passing, which filte… (see more)rs the neighborhood node information. Though effective for various tasks, in this paper, we show that they are potentially a problematic factor underlying all GNN methods for learning on certain datasets, as they force the node representations similar, making the nodes gradually lose their identity and become indistinguishable. Hence, we augment the aggregation operations with their dual, i.e. diversification operators that make the node more distinct and preserve the identity. Such augmentation replaces the aggregation with a two-channel filtering process that, in theory, is beneficial for enriching the node representations. In practice, the proposed two-channel filters can be easily patched on existing GNN methods with diverse training strategies, including spectral and spatial (message passing) methods. In the experiments, we observe desired characteristics of the models and significant performance boost upon the baselines on 9 node classification tasks.
2022-11-21
NeurIPS.cc/2022/Workshop/GLFrontiers (published)
doi.org
openreview.net