Publications

FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting

He Zhu

Jun Bai

Na Li

Xiaoxiao Li

Dianbo Liu

David L. Buckeridge

Yue Li

Federated learning (FL) enables collaborative analysis of decentralized medical data while preserving patient privacy. However, the covariat… (voir plus)e shift from demographic and clinical differences can reduce model generalizability. We propose FedWeight, a novel FL framework that mitigates covariate shift by reweighting patient data from the source sites using density estimators, allowing the trained model to better align with the distribution of the target site. To support unsupervised applications, we introduce FedWeight ETM, a federated embedded topic model. We evaluated FedWeight in cross-site FL on the eICU dataset and cross-dataset FL between eICU and MIMIC III. FedWeight consistently outperforms standard FL baselines in predicting ICU mortality, ventilator use, sepsis diagnosis, and length of stay. SHAP-based interpretation and ETM-based topic modeling reveal improved identification of clinically relevant characteristics and disease topics associated with ICU readmission.

2024-12-31

npj Digital Medicine (publié)

A "fine-cuts" approach disentangling psychopathic, autistic and alexithymic traits in their associations with affective, cognitive and motor empathy

Julia Ayache

Nikki Stevenson

Elisha Patel

Alexander Sumich

Guillaume Dumas

Nadja Heym

2024-12-31

Personality and Individual Differences (publié)

RL Fine-Tuning Heals OOD Forgetting in SFT

Sicheng Lyu

Mohammad Hamdaqa

The two-stage fine-tuning paradigm of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has empirically shown better reas… (voir plus)oning performance than one-stage SFT for the post-training of Large Language Models (LLMs). However, the evolution and mechanism behind the synergy of SFT and RL are still under-explored and inconclusive. In our study, we find the well-known claim "SFT memorizes, RL generalizes" is over-simplified, and discover that: (1) OOD performance peaks at the early stage of SFT and then declines (OOD forgetting), the best SFT checkpoint cannot be captured by training/test loss; (2) the subsequent RL stage does not generate fundamentally better OOD capability, instead it plays an \textbf{OOD restoration} role, recovering the lost reasoning ability during SFT; (3) The recovery ability has boundaries, \ie{} \textbf{if SFT trains for too short or too long, RL cannot recover the lost OOD ability;} (4) To uncover the underlying mechanisms behind the forgetting and restoration process, we employ SVD analysis on parameter matrices, manually edit them, and observe their impacts on model performance. Unlike the common belief that the shift of model capacity mainly results from the changes of singular values, we find that they are actually quite stable throughout fine-tuning. Instead, the OOD behavior strongly correlates with the \textbf{rotation of singular vectors}. Our findings re-identify the roles of SFT and RL in the two-stage fine-tuning and discover the rotation of singular vectors as the key mechanism. %reversing the rotations induced by SFT, which shows recovery from forgetting, whereas imposing the SFT parameter directions onto a RL-tuned model results in performance degradation. Code is available at https://github.com/xiaodanguoguo/RL_Heals_SFT

2024-12-31

arXiv (prépublication)

fLSA: Learning Semantic Structures in Document Collections Using Foundation Models

Weijia Xu

Nebojsa Jojic

Nicolas Roux

Humans can learn to solve new tasks by inducing high-level strategies from example solutions to similar problems and then adapting these str… (voir plus)ategies to solve unseen problems. Can we use large language models to induce such high-level structure from example documents or solutions? We introduce fLSA, a foundation-model-based Latent Semantic Analysis method that iteratively clusters and tags document segments based on document-level contexts. These tags can be used to model the latent structure of given documents and for hierarchical sampling of new texts. Our experiments on story writing, math, and multi-step reasoning datasets demonstrate that fLSA tags are more informative in reconstructing the original texts than existing tagging methods. Moreover, when used for hierarchical sampling, fLSA tags help expand the output space in the right directions that lead to correct solutions more often than direct sampling and hierarchical sampling with existing tagging methods. Code: https://github.com/microsoft/fLSA

2024-12-31

EMNLP (publié)

3D Foundation Model-Based Loop Closing for Decentralized Collaborative SLAM

Pierre-Yves Lajoie

Benjamin Ramtoula

Daniele De Martini

Giovanni Beltrame

Decentralized Collaborative Simultaneous Localization and Mapping (C-SLAM) techniques often struggle to identify map overlaps due to signifi… (voir plus)cant viewpoint variations among robots. Motivated by recent advancements in 3D foundation models, which can register images despite large viewpoint differences, we propose a robust loop closing approach that leverages these models to establish inter-robot measurements. In contrast to resource-intensive methods requiring full 3D reconstruction within a centralized map, our approach integrates foundation models into existing SLAM pipelines, yielding scalable and robust multi-robot mapping. Our contributions include: 1) integrating 3D foundation models to reliably estimate relative poses from monocular image pairs within decentralized C-SLAM; 2) introducing robust outlier mitigation techniques critical to the use of these relative poses and 3) developing specialized pose graph optimization formulations that efficiently resolve scale ambiguities. We evaluate our method against state-of-the-art approaches, demonstrating improvements in localization and mapping accuracy, alongside significant gains in computational and memory efficiency. These results highlight the potential of our approach for deployment in large-scale multi-robot scenarios.

2024-12-31

IEEE Robotics Autom. Lett. (publié)

From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons

Andrew Szot

Bogdan Mazoure

Omar Attia

Aleksei Timofeev

Harsh Agrawal

R Devon Hjelm

Zhe Gan

Zsolt Kira

Alexander T Toshev

We examine the capability of Multimodal Large Language Models (MLLMs) to tackle diverse domains that extend beyond the traditional language … (voir plus)and vision tasks these models are typically trained on. Specifically, our focus lies in areas such as Embodied AI, Games, UI Control, and Planning. To this end, we introduce a process of adapting an MLLM to a Generalist Embodied Agent (GEA). GEA is a single unified model capable of grounding itself across these varied domains through a multi-embodiment action tokenizer. GEA is trained with supervised learning on a large dataset of embodied experiences and with online RL in interactive simulators. We explore the data and algorithmic choices necessary to develop such a model. Our findings reveal the importance of training with cross-domain data and online RL for building generalist agents. The final GEA model achieves strong generalization performance to unseen tasks across diverse benchmarks compared to other generalist models and benchmark-specific approaches.

2024-12-31

Computer Vision and Pattern Recognition (publié)

Giuseppe Alessio D'Inverno

Generalization Limits of Graph Neural Networks in Identity Effects Learning

Simone Brugiapaglia

Mirco Ravanelli

Graph Neural Networks (GNNs) have emerged as a powerful tool for data-driven learning on various graph domains. They are usually based on a … (voir plus)message-passing mechanism and have gained increasing popularity for their intuitive formulation, which is closely linked to the Weisfeiler-Lehman (WL) test for graph isomorphism to which they have been proven equivalent in terms of expressive power. In this work, we establish new generalization properties and fundamental limits of GNNs in the context of learning so-called identity effects, i.e., the task of determining whether an object is composed of two identical components or not. Our study is motivated by the need to understand the capabilities of GNNs when performing simple cognitive tasks, with potential applications in computational linguistics and chemistry. We analyze two case studies: (i) two-letters words, for which we show that GNNs trained via stochastic gradient descent are unable to generalize to unseen letters when utilizing orthogonal encodings like one-hot representations; (ii) dicyclic graphs, i.e., graphs composed of two cycles, for which we present positive existence results leveraging the connection between GNNs and the WL test. Our theoretical analysis is supported by an extensive numerical study.

2024-12-31

Neural Networks (publié)

A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens

David Dobre

2024-12-31

arXiv.org (prépublication)

Geometric Signatures of Compositionality Across a Language Model's Lifetime

Jin Hwa Lee

Thomas Jiralerspong

Lei Yu

Yoshua Bengio

Emily Cheng

Compositionality, the notion that the meaning of an expression is constructed from the meaning of its parts and syntactic rules, permits the… (voir plus) infinite productivity of human language. For the first time, artificial language models (LMs) are able to match human performance in a number of compositional generalization tasks. However, much remains to be understood about the representational mechanisms underlying these abilities. We take a high-level geometric approach to this problem by relating the degree of compositionality in a dataset to the intrinsic dimensionality of its representations under an LM, a measure of feature complexity. We find not only that the degree of dataset compositionality is reflected in representations' intrinsic dimensionality, but that the relationship between compositionality and geometric complexity arises due to learned linguistic features over training. Finally, our analyses reveal a striking contrast between linear and nonlinear dimensionality, showing that they respectively encode formal and semantic aspects of linguistic composition.

2024-12-31

ACL (1) (publié)

GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities

Victor May

Samira Ebrahimi Kahou

Massimo Caccia

The rapid evolution of software libraries poses a considerable hurdle for code generation, necessitating continuous adaptation to frequent v… (voir plus)ersion updates while preserving backward compatibility. While existing code evolution benchmarks provide valuable insights, they typically lack execution-based evaluation for generating code compliant with specific library versions. To address this, we introduce GitChameleon 2.0, a novel, meticulously curated dataset comprising 328 Python code completion problems, each conditioned on specific library versions and accompanied by executable unit tests. GitChameleon 2.0 rigorously evaluates the capacity of contemporary large language models (LLMs), LLM-powered agents, code assistants, and RAG systems to perform version-conditioned code generation that demonstrates functional accuracy through execution. Our extensive evaluations indicate that state-of-the-art systems encounter significant challenges with this task; enterprise models achieving baseline success rates in the 48-51% range, underscoring the intricacy of the problem. By offering an execution-based benchmark emphasizing the dynamic nature of code libraries, GitChameleon 2.0 enables a clearer understanding of this challenge and helps guide the development of more adaptable and dependable AI code generation methods. We make the dataset and evaluation code publicly available at https://github.com/mrcabbage972/GitChameleonBenchmark.

2024-12-31

arXiv (prépublication)

A Guide to Misinformation Detection Data and Evaluation

Camille Thibault

Jacob-Junqi Tian

Gabrielle Peloquin-Skulski

Taylor Lynn Curtis

James Zhou

Florence Laflamme

Luke Yuxiang Guan

Reihaneh Rabbany

Jean-François Godbout

Kellin Pelrine

Misinformation is a complex societal issue, and mitigating solutions are difficult to create due to data deficiencies. To address this, we h… (voir plus)ave curated the largest collection of (mis)information datasets in the literature, totaling 75. From these, we evaluated the quality of 36 datasets that consist of statements or claims, as well as the 9 datasets that consist of data in purely paragraph form. We assess these datasets to identify those with solid foundations for empirical work and those with flaws that could result in misleading and non-generalizable results, such as spurious correlations, or examples that are ambiguous or otherwise impossible to assess for veracity. We find the latter issue is particularly severe and affects most datasets in the literature. We further provide state-of-the-art baselines on all these datasets, but show that regardless of label quality, categorical labels may no longer give an accurate evaluation of detection model performance. Finally, we propose and highlight Evaluation Quality Assurance (EQA) as a tool to guide the field toward systemic solutions rather than inadvertently propagating issues in evaluation. Overall, this guide aims to provide a roadmap for higher quality data and better grounded evaluations, ultimately improving research in misinformation detection. All datasets and other artifacts are available at https://misinfo-datasets.complexdatalab.com/.

2024-12-31

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (publié)