Publications

Explicit Knowledge Factorization Meets In-Context Learning: What Do We Gain?

2024-03-04

ICLR.cc/2024/Workshop/R2-FM (poster)

Optimisation of quantitative brain diffusion-relaxation MRI acquisition protocols with physics-informed machine learning.

Álvaro Planchuelo-Gómez

Maxime Descoteaux

Hugo Larochelle

Jana Hutter

Derek K. Jones

C. Tax

2024-03-04

Medical Image Analysis (publié)

doi.org

Plant invasion in Mediterranean Europe: current hotspots and future scenarios

Luigi Cao Pinna

Laure Gallien

Laura J. Pollock

Irena Axmanová

Milan Chytrý

Marco Malavasi

Alicia T. R. Acosta

Juan Antonio Campos

Marta Carboni

The Mediterranean Basin has historically been subject to alien plant invasions that threaten its unique biodiversity. This seasonally dry an… (voir plus)d densely populated region is undergoing severe climatic and socioeconomic changes, and it is unclear whether these changes will worsen or mitigate plant invasions. Predictions are often biased, as species may not be in equilibrium in the invaded environment, depending on their invasion stage and ecological characteristics. To address future predictions uncertainty, we identified invasion hotspots across multiple biased modelling scenarios and ecological characteristics of successful invaders. We selected 92 alien plant species widespread in Mediterranean Europe and compiled data on their distribution in the Mediterranean and worldwide. We combined these data with environmental and propagule pressure variables to model global and regional species niches, and map their current and future habitat suitability. We identified invasion hotspots, examined their potential future shifts, and compared the results of different modelling strategies. Finally, we generalised our findings by using linear models to determine the traits and biogeographic features of invaders most likely to benefit from global change. Currently, invasion hotspots are found near ports and coastlines throughout Mediterranean Europe. However, many species occupy only a small portion of the environmental conditions to which they are preadapted, suggesting that their invasion is still an ongoing process. Future conditions will lead to declines in many currently widespread aliens, which will tend to move to higher elevations and latitudes. Our trait models indicate that future climates will generally favour species with conservative ecological strategies that can cope with reduced water availability, such as those with short stature and low specific leaf area. Taken together, our results suggest that in future environments, these conservative aliens will move farther from the introduction areas and upslope, threatening mountain ecosystems that have been spared from invasions so far.

2024-03-04

Ecography (publié)

doi.org

Smoothness-Adaptive Sharpness-Aware Minimization for Finding Flatter Minima

Hiroki Naganuma

Junhyung Lyle Kim

Anastasios Kyrillidis

Ioannis Mitliagkas

The sharpness-aware minimization (SAM) procedure recently gained increasing attention due to its favorable generalization ability to unseen … (voir plus)data. SAM aims to find flatter (local) minima, utilizing a minimax objective. An immediate challenge in the application of SAM is the adjustment of two pivotal step sizes, which significantly influence its effectiveness. We introduce a novel, straightforward approach for adjusting step sizes that adapts to the smoothness of the objective function, thereby reducing the necessity for manual tuning. This method, termed Smoothness-Adaptive SAM (SA-SAM), not only simplifies the optimization process but also promotes the method's inherent tendency to converge towards flatter minima, enhancing performance in specific models.

2024-03-04

ICLR.cc/2024/Workshop/PML4LRS (poster)

openreview.net

The World Health Organization as an engine of ideational robustness

Jean-Louis Denis

Gaëlle Foucault

Pierre Larouche

Catherine Régis

Miriam Cohen

Marie-Andree Girard

The paper focuses on the role of the World Health Organization (WHO) in promoting a healthy world population as a generative and robust idea… (voir plus) within health policy. The WHO’s health credo transcends national boundaries to promote health globally. It is embedded in norms, values, and standards promulgated by the organization and contributes in shaping the health responses of national governments. Ideational robustness refers to the ability of the WHO to adapt its health credo to changing contexts and circumstances, thus promoting the legitimacy of an international health order. Disturbances, including the Covid-19 pandemic, test the credo’s robustness, forcing the WHO to constantly work at reframing ideas to adapt to political forces and competing logics that structure the field of international health. Empirically, the paper is based on an historical analysis of the evolution of the health credo of the WHO since its inception. Qualitative content analysis of secondary sources, such as policy documents, explores how ideational work performed by WHO leaders impacts on the organization’s position and legitimacy. Ideational robustness appears to be largely influenced by leadership vision, preexisting organizational structure, and the political economy of international health. Ideational robustness appears as a powerful yet insufficient ingredient of policy success.

2024-03-04

Policy & Society (publié)

doi.org

F$^3$low: Frame-to-Frame Coarse-grained Molecular Dynamics with SE(3) Guided Flow Matching

Shaoning Li

Yusong Wang

Mingyu Li

Bin Shao

Nanning Zheng

Zhang Jian

Jian Tang

2024-03-03

ICLR.cc/2024/Workshop/GEM (poster)

openreview.net

Enhancing and Evaluating Logical Reasoning Abilities of Large Language Models

Shujie Deng

Honghua Dong

Xujie Si

2024-03-03

ICLR.cc/2024/Workshop/SeT_LLM (publié)

openreview.net

Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations

Bozitao Zhong

The protein dynamics are common and important for their biological functions and properties, the study of which usually involves time-consum… (voir plus)ing molecular dynamics (MD) simulations *in silico*. Recently, generative models has been leveraged as a surrogate sampler to obtain conformation ensembles with orders of magnitude faster and without requiring any simulation data (a "zero-shot" inference). However, being agnostic of the underlying energy landscape, the accuracy of such generative model may still be limited. In this work, we explore the few-shot setting of such pre-trained generative sampler which incorporates MD simulations in a tractable manner. Specifically, given a target protein of interest, we first acquire some seeding conformations from the pre-trained sampler followed by a number of physical simulations in parallel starting from these seeding samples. Then we fine-tuned the generative model using the simulation trajectories above to become a target-specific sampler. Experimental results demonstrated the superior performance of such few-shot conformation sampler at a tractable computational cost.

2024-03-03

ICLR.cc/2024/Workshop/GEM (poster)

openreview.net

Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok

Tikeng Notsawo Pascal Junior

Pascal Notsawo

2024-03-03

ICLR.cc/2024/Workshop/ME-FoMo (poster)

doi.org

openreview.net

Self-evaluation and self-prompting to improve the reliability of LLMs

Alexandre Piché

Aristides Milios

Dzmitry Bahdanau

Christopher Pal

In order to safely deploy Large Language Models (LLMs), they must be capable of dynamically adapting their behavior based on their level of … (voir plus)knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to as self-restraint, is non-trivial to teach since it depends on the internal knowledge of an LLM. By default, LLMs are trained to maximize the next token likelihood which does not teach the model to modulate its answer based on its level of uncertainty. In order to learn self-restraint, we devise a simple objective that can encourage the model to produce generation that the model is confident in. To optimize this objective, we introduce ReSearch, an iterative search algorithm based on self-evaluation and self-prompting. Our method results in fewer hallucinations overall, both for known and unknown topics, as the model learns to selectively restrain itself. In addition, our method elegantly incorporates the ability to decline, when the model assesses that it cannot provide a response without a high proportion of hallucination.

2024-03-03

ICLR.cc/2024/Workshop/SeT_LLM (publié)

openreview.net

Structure-Informed Protein Language Model

Zuobai Zhang

Jiarui Lu

Vijil Chenthamarakshan

Aurelie Lozano

Payel Das

Jian Tang

Protein language models are a powerful tool for learning protein representations through pre-training on vast protein sequence datasets. Ho… (voir plus)wever, traditional protein language models lack explicit structural supervision, despite its relevance to protein function. To address this issue, we introduce the integration of remote homology detection to distill structural information into protein language models without requiring explicit protein structures as input. We evaluate the impact of this structure-informed training on downstream protein function prediction tasks. Experimental results reveal consistent improvements in function annotation accuracy for EC number and GO term prediction. Performance on mutant datasets, however, varies based on the relationship between targeted properties and protein structures. This underscores the importance of considering this relationship when applying structure-aware training to protein function prediction tasks. Code and model weights will be made available upon acceptance.

2024-03-03

GEM @ International Conference on Learning Representations (poster)

doi.org

openreview.net

Temporal Graph Analysis with TGX

Real-world networks, with their evolving relations, are best captured as temporal graphs. However, existing software libraries are largely d… (voir plus)esigned for static graphs where the dynamic nature of temporal graphs is ignored. Bridging this gap, we introduce TGX, a Python package specially designed for analysis of temporal networks that encompasses an automated pipeline for data loading, data processing, and analysis of evolving graphs. TGX provides access to eleven built-in datasets and eight external Temporal Graph Benchmark (TGB) datasets as well as any novel datasets in the .csv format. Beyond data loading, TGX facilitates data processing functionalities such as discretization of temporal graphs and node subsampling to accelerate working with larger datasets. For comprehensive investigation, TGX offers network analysis by providing a diverse set of measures, including average node degree and the evolving number of nodes and edges per timestamp. Additionally, the package consolidates meaningful visualization plots indicating the evolution of temporal patterns, such as Temporal Edge Appearance (TEA) and Temporal Edge Trafficc (TET) plots. The TGX package is a robust tool for examining the features of temporal graphs and can be used in various areas like studying social networks, citation networks, and tracking user interactions. We plan to continuously support and update TGX based on community feedback. TGX is publicly available on: https://github.com/ComplexData-MILA/TGX.

2024-03-03

Proceedings of the 17th ACM International Conference on Web Search and Data Mining (publié)

doi.org

arxiv.org

La plateforme Mila Ventures

Boussole des politiques en IA

Séances d'information virtuelles

Publications

La plateforme Mila Ventures

Boussole des politiques en IA

Séances d'information virtuelles

Mots-clés populaires:

Publications