Publications

Length Independent PAC-Bayes Bounds for Simple RNNs

Volodimir Mitarchuk

Clara Lacroce

Rémi Eyraud

Rémi Emonet

Amaury Habrard

Guillaume Rabusseau

2024-04-17

Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)

proceedings.mlr.press

Longitudinal microstructural changes in 18 amygdala nuclei resonate with cortical circuits and phenomics

Karam Ghanem

Karin Saltoun

Aparna Suvrathan

Bogdan Draganski

Danilo Bzdok

The amygdala nuclei modulate distributed neural circuits that most likely evolved to respond to environmental threats and opportunities. So … (see more)far, the specific role of unique amygdala nuclei in the context processing of salient environmental cues lacks adequate characterization across neural systems and over time. Here, we present amygdala nuclei morphometry and behavioral findings from longitudinal population data (>1400 subjects, age range 40-69 years, sampled 2-3 years apart): the UK Biobank offers exceptionally rich phenotyping along with brain morphology scans. This allows us to quantify how 18 microanatomical amygdala subregions undergo plastic changes in tandem with coupled neural systems and delineating their associated phenome-wide profiles. In the context of population change, the basal, lateral, accessory basal, and paralaminar nuclei change in lockstep with the prefrontal cortex, a region that subserves planning and decision-making. The central, medial and cortical nuclei are structurally coupled with the insular and anterior-cingulate nodes of the salience network, in addition to the MT/V5, basal ganglia, and putamen, areas proposed to represent internal bodily states and mediate attention to environmental cues. The central nucleus and anterior amygdaloid area are longitudinally tied with the inferior parietal lobule, known for a role in bodily awareness and social attention. These population-level amygdala-brain plasticity regimes in turn are linked with unique collections of phenotypes, ranging from social status and employment to sleep habits and risk taking. The obtained structural plasticity findings motivate hypotheses about the specific functions of distinct amygdala nuclei in humans.

2024-04-17

Communications Biology (published)

doi.org

Multi-phase black-hole feedback and a bright [CII] halo in a Lo-BAL quasar at $z\sim6.6$

Manuela Bischetti

Hyunseop 현섭 Choi 최

Fabrizio Fiore

Chiara Feruglio

Stefano Carniani

Valentina D'Odorico

Eduardo Banados

Huanqing Chen

Roberto Decarli

Simona Gallerani

J. Hlavacek-Larrondo

Samuel Lai

Karen M. Leighly

Chiara Mazzucchelli

Laurence Perreault-Levasseur

Roberta Tripodi

Fabian Walter

Feige Wang

Jinyi Yang

Maria Vittoria Zanchettin … (see 1 more)

Yongda Zhu

2024-04-17

ArXiv (preprint)

doi.org

arxiv.org

Multi-resolution Time-Series Transformer for Long-term Forecasting

Yitian Zhang

Liheng Ma

Soumyasundar Pal

Yingxue Zhang

Mark J. Coates

2024-04-17

Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)

doi.org

proceedings.mlr.press

Optimal Zero-Shot Detector for Multi-Armed Attacks

Federica Granese

Marco Romanelli

Pablo Piantanida

This paper explores a scenario in which a malicious actor employs a multi-armed attack strategy to manipulate data samples, offering them va… (see more)rious avenues to introduce noise into the dataset. Our central objective is to protect the data by detecting any alterations to the input. We approach this defensive strategy with utmost caution, operating in an environment where the defender possesses significantly less information compared to the attacker. Specifically, the defender is unable to utilize any data samples for training a defense model or verifying the integrity of the channel. Instead, the defender relies exclusively on a set of pre-existing detectors readily available"off the shelf". To tackle this challenge, we derive an innovative information-theoretic defense approach that optimally aggregates the decisions made by these detectors, eliminating the need for any training data. We further explore a practical use-case scenario for empirical evaluation, where the attacker possesses a pre-trained classifier and launches well-known adversarial attacks against it. Our experiments highlight the effectiveness of our proposed solution, even in scenarios that deviate from the optimal setup.

2024-04-17

Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)

doi.org

proceedings.mlr.press

Tackling the XAI Disagreement Problem with Regional Explanations

Gabriel Laberge

Yann Batiste Pequignot

Mario Marchand

Foutse Khomh

2024-04-17

Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)

proceedings.mlr.press

Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences

Shreya Shankar

J.D. Zamfirescu-Pereira

Bjorn Hartmann

Aditya G Parameswaran

Ian Arawjo

2024-04-17

ArXiv (preprint)

doi.org

arxiv.org

Asynchronous Algorithmic Alignment with Cocycles

Andrew Joseph Dudzik

Tamara von Glehn

Razvan Pascanu

Petar Veličković

State-of-the-art neural algorithmic reasoners make use of message passing in graph neural networks (GNNs). But typical GNNs blur the distinc… (see more)tion between the definition and invocation of the message function, forcing a node to send messages to its neighbours at every layer, synchronously. When applying GNNs to learn to execute dynamic programming algorithms, however, on most steps only a handful of the nodes would have meaningful updates to send. One, hence, runs the risk of inefficiencies by sending too much irrelevant data across the graph. But more importantly, many intermediate GNN steps have to learn the identity functions, which is a non-trivial learning problem. In this work, we explicitly separate the concepts of node state update and message function invocation. With this separation, we obtain a mathematical formulation that allows us to reason about asynchronous computation in both algorithms and neural networks. Our analysis yields several practical implementations of synchronous scalable GNN layers that are provably invariant under various forms of asynchrony.

2024-04-16

Proceedings of the Second Learning on Graphs Conference (published)

doi.org

proceedings.mlr.press

Inferring dynamic regulatory interaction graphs from time series data with perturbations

Dhananjay Bhaskar

Sumner Magruder

Edward De Brouwer

Matheo Morales

Aarthi Venkat

Frederik Wenkel

Guy Wolf

Smita Krishnaswamy

Complex systems are characterized by intricate interactions between entities that evolve dynamically over time. Accurate inference of these … (see more)dynamic relationships is crucial for understanding and predicting system behavior. In this paper, we propose Regulatory Temporal Interaction Network Inference (RiTINI) for inferring time-varying interaction graphs in complex systems using a novel combination of space-and-time graph attentions and graph neural ordinary differential equations (ODEs). RiTINI leverages time-lapse signals on a graph prior, as well as perturbations of signals at various nodes in order to effectively capture the dynamics of the underlying system. This approach is distinct from traditional causal inference networks, which are limited to inferring acyclic and static graphs. In contrast, RiTINI can infer cyclic, directed, and time-varying graphs, providing a more comprehensive and accurate representation of complex systems. The graph attention mechanism in RiTINI allows the model to adaptively focus on the most relevant interactions in time and space, while the graph neural ODEs enable continuous-time modeling of the system's dynamics. We evaluate RiTINI's performance on various simulated and real-world datasets, demonstrating its state-of-the-art capability in inferring interaction graphs compared to previous methods.

2024-04-16

Proceedings of the Second Learning on Graphs Conference (published)

doi.org

proceedings.mlr.press

Latent Space Representations of Neural Algorithmic Reasoners

Vladimir V. Mirjani'c

Razvan Pascanu

Petar Velivckovi'c University of Cambridge

Petar Veličković

Google Deepmind

Neural Algorithmic Reasoning (NAR) is a research area focused on designing neural architectures that can reliably capture classical computat… (see more)ion, usually by learning to execute algorithms. A typical approach is to rely on Graph Neural Network (GNN) architectures, which encode inputs in high-dimensional latent spaces that are repeatedly transformed during the execution of the algorithm. In this work we perform a detailed analysis of the structure of the latent space induced by the GNN when executing algorithms. We identify two possible failure modes: (i) loss of resolution, making it hard to distinguish similar values; (ii) inability to deal with values outside the range observed during training. We propose to solve the first issue by relying on a softmax aggregator, and propose to decay the latent space in order to deal with out-of-range values. We show that these changes lead to improvements on the majority of algorithms in the standard CLRS-30 benchmark when using the state-of-the-art Triplet-GMPNN processor. Our code is available at https://github.com/mirjanic/nar-latent-spaces

2024-04-16

Proceedings of the Second Learning on Graphs Conference (published)

doi.org

proceedings.mlr.press

Neural Semantic Surface Maps

Luca Morreale

Noam Aigerman

Vladimir Kim

Niloy J. Mitra

2024-04-16

Computer Graphics Forum (published)

doi.org