Publications

Generative AI in Software Engineering Must Be Human-Centered: The Copenhagen Manifesto
Daniel Russo
Sebastian Baltes
Niels van Berkel
Paris Avgeriou
Fabio Calefato
Beatriz Cabrero-Daniel
Gemma Catolino
Jürgen Cito
Neil Ernst
Thomas Fritz
Hideaki Hata
Reid Holmes
Maliheh Izadi
Foutse Khomh
Mikkel Baun Kjærgaard
Grischa Liebel
Alberto Lluch Lafuente
Stefano Lambiase
Walid Maalej
Gail Murphy … (see 15 more)
Nils Brede Moe
Gabrielle O'Brien
Elda Paja
Mauro Pezzè
John Stouby Persson
Rafael Prikladnicki
Paul Ralph
Martin P. Robillard
Thiago Rocha Silva
Klaas-Jan Stol
Margaret-Anne Storey
Viktoria Stray
Paolo Tell
Christoph Treude
Bogdan Vasilescu
2024-04-30
Journal of Systems and Software (published)
doi.org
Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
Stefan Horoi
Albert Manuel Orozco Camacho
Eugene Belilovsky
Guy Wolf
Combining the predictions of multiple trained models through ensembling is generally a good way to improve accuracy by leveraging the differ… (see more)ent learned features of the models, however it comes with high computational and storage costs. Model fusion, the act of merging multiple models into one by combining their parameters reduces these costs but doesn't work as well in practice. Indeed, neural network loss landscapes are high-dimensional and non-convex and the minima found through learning are typically separated by high loss barriers. Numerous recent works have been focused on finding permutations matching one network features to the features of a second one, lowering the loss barrier on the linear path between them in parameter space. However, permutations are restrictive since they assume a one-to-one mapping between the different models' neurons exists. We propose a new model merging algorithm, CCA Merge, which is based on Canonical Correlation Analysis and aims to maximize the correlations between linear combinations of the model features. We show that our alignment method leads to better performances than past methods when averaging models trained on the same, or differing data splits. We also extend this analysis into the harder setting where more than 2 models are merged, and we find that CCA Merge works significantly better than past methods. Our code is publicly available at https://github.com/shoroi/align-n-merge
2024-04-30
International Conference on Machine Learning (poster)
doi.org
proceedings.mlr.press
Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization
Idan Attias
Gintare Karolina Dziugaite
MAHDI HAGHIFAM
Roi Livni
Daniel M. Roy
In this work, we investigate the interplay between memorization and learning in the context of \emph{stochastic convex optimization} (SCO). … (see more)We define memorization via the information a learning algorithm reveals about its training data points. We then quantify this information using the framework of conditional mutual information (CMI) proposed by Steinke and Zakynthinou (2020). Our main result is a precise characterization of the tradeoff between the accuracy of a learning algorithm and its CMI, answering an open question posed by Livni (2023). We show that, in the
2024-04-30
ICML.cc/2024/Conference (oral)
doi.org
openreview.net
Language-guided Skill Learning with Temporal Variational Inference
Haotian Fu
Pratyusha Sharma
Elias Stengel-Eskin
George Konidaris
Nicolas Le Roux
Marc-Alexandre Côté
Xingdi Yuan
We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose… (see more) an initial segmentation of the trajectories. Following that, a hierarchical variational inference framework incorporates the LLM-generated segmentation information to discover reusable skills by merging trajectory segments. To further control the trade-off between compression and reusability, we introduce a novel auxiliary objective based on the Minimum Description Length principle that helps guide this skill discovery process. Our results demonstrate that agents equipped with our method are able to discover skills that help accelerate learning and outperform baseline skill learning approaches on new long-horizon tasks in BabyAI, a grid world navigation environment, as well as ALFRED, a household simulation environment.
2024-04-30
ICML.cc/2024/Conference (poster)
doi.org
proceedings.mlr.press
Learning to Scale Logits for Temperature-Conditional GFlowNets
Minsu Kim
Joohwan Ko
Dinghuai Zhang
Ling Pan
Taeyoung YUN
Woo Chang Kim
Jinkyoo Park
Emmanuel Bengio
Yoshua Bengio
GFlowNets are probabilistic models that sequentially generate compositional structures through a stochastic policy. Among GFlowNets, tempera… (see more)ture-conditional GFlowNets can introduce temperature-based controllability for exploration and exploitation. We propose \textit{Logit-scaling GFlowNets} (Logit-GFN), a novel architectural design that greatly accelerates the training of temperature-conditional GFlowNets. It is based on the idea that previously proposed approaches introduced numerical challenges in the deep network training, since different temperatures may give rise to very different gradient profiles as well as magnitudes of the policy's logits. We find that the challenge is greatly reduced if a learned function of the temperature is used to scale the policy's logits directly. Also, using Logit-GFN, GFlowNets can be improved by having better generalization capabilities in offline learning and mode discovery capabilities in online learning, which is empirically verified in various biological and chemical tasks. Our code is available at https://github.com/dbsxodud-11/logit-gfn
2024-04-30
ICML.cc/2024/Conference (poster)
doi.org
proceedings.mlr.press
Learning the meanings of function words from grounded language using a visual question answering model
Eva Portelance
Michael C. Frank
Dan Jurafsky
Interpreting a seemingly-simple function word like "or", "behind", or "more" can require logical, numerical, and relational reasoning. How a… (see more)re such words learned by children? Prior acquisition theories have often relied on positing a foundation of innate knowledge. Yet recent neural-network based visual question answering models apparently can learn to use function words as part of answering questions about complex visual scenes. In this paper, we study what these models learn about function words, in the hope of better understanding how the meanings of these words can be learnt by both models and children. We show that recurrent models trained on visually grounded language learn gradient semantics for function words requiring spatial and numerical reasoning. Furthermore, we find that these models can learn the meanings of logical connectives and and or without any prior knowledge of logical reasoning, as well as early evidence that they are sensitive to alternative expressions when interpreting language. Finally, we show that word learning difficulty is dependent on frequency in models' input. Our findings offer proof-of-concept evidence that it is possible to learn the nuanced interpretations of function words in visually grounded context by using non-symbolic general statistical learning algorithms, without any prior knowledge of linguistic meaning.
2024-04-30
Cognitive Science (published)
doi.org
arxiv.org
MixEHR-SurG: a joint proportional hazard and guided topic model for inferring mortality-associated topics from electronic health records
Yixuan Li
Ariane Marelli
Archer Y. Yang
Yue Li
Survival models can help medical practitioners to evaluate the prognostic importance of clinical variables to patient outcomes such as morta… (see more)lity or hospital readmission and subsequently design personalized treatment regimes. Electronic Health Records (EHRs) hold the promise for large-scale survival analysis based on systematically recorded clinical features for each patient. However, existing survival models either do not scale to high dimensional and multi-modal EHR data or are difficult to interpret. In this study, we present a supervised topic model called MixEHR-SurG to simultaneously integrate heterogeneous EHR data and model survival hazard. Our contributions are three-folds: (1) integrating EHR topic inference with Cox proportional hazards likelihood; (2) integrating patient-specific topic hyperparameters using the PheCode concepts such that each topic can be identified with exactly one PheCode-associated phenotype; (3) multi-modal survival topic inference. This leads to a highly interpretable survival topic model that can infer PheCode-specific phenotype topics associated with patient mortality. We evaluated MixEHR-SurG using a simulated dataset and two real-world EHR datasets: the Quebec Congenital Heart Disease (CHD) data consisting of 8,211 subjects with 75,187 outpatient claim records of 1,767 unique ICD codes; the MIMIC-III consisting of 1,458 subjects with multi-modal EHR records. Compared to the baselines, MixEHR-SurG achieved a superior dynamic AUROC for mortality prediction, with a mean AUROC score of 0.89 in the simulation dataset and a mean AUROC of 0.645 on the CHD dataset. Qualitatively, MixEHR-SurG associates severe cardiac conditions with high mortality risk among the CHD patients after the first heart failure hospitalization and critical brain injuries with increased mortality among the MIMIC-III patients after their ICU discharge.
2024-04-30
Journal of Biomedical Informatics (published)
doi.org
arxiv.org
Mixtures of Experts Unlock Parameter Scaling for Deep RL
Johan Obando-Ceron
Ghada Sokar
Timon Willi
Clare Lyle
Jesse Farebrother
Jakob Foerster
Karolina Dziugaite
Doina Precup
Pablo Samuel Castro
The recent rapid progress in (self) supervised learning models is in large part predicted by empirical scaling laws: a model's performance s… (see more)cales proportionally to its size. Analogous scaling laws remain elusive for reinforcement learning domains, however, where increasing the parameter count of a model often hurts its final performance. In this paper, we demonstrate that incorporating Mixture-of-Expert (MoE) modules, and in particular Soft MoEs (Puigcerver et al., 2023), into value-based networks results in more parameter-scalable models, evidenced by substantial performance increases across a variety of training regimes and model sizes. This work thus provides strong empirical evidence towards developing scaling laws for reinforcement learning.
2024-04-30
ICML.cc/2024/Conference (spotlight)
doi.org
proceedings.mlr.press
Nash Learning from Human Feedback
Remi Munos
Michal Valko
Daniele Calandriello
Mohammad Gheshlaghi Azar
Mark Rowland
Zhaohan Daniel Guo
Yunhao Tang
Matthieu Geist
Thomas Mesnard
Côme Fiegel
Andrea Michi
Marco Selvi
Sertan Girgin
Nikola Momchev
Olivier Bachem
Daniel J Mankowitz
Doina Precup
Bilal Piot
Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human pref… (see more)erences. Traditionally, RLHF involves the initial step of learning a reward model from pairwise human feedback, i.e., expressed as preferences between pairs of text generations. Subsequently, the LLM’s policy is fine-tuned to maximize the reward through a reinforcement learning algorithm. In this study, we introduce an alternative pipeline for the fine-tuning of LLMs using pairwise human feedback. Our approach entails the initial learning of a pairwise preference model, which is conditioned on two inputs (instead of a single input in the case of a reward model) given a prompt, followed by the pursuit of a policy that consistently generates responses preferred over those generated by any competing policy, thus defining the Nash equilibrium of this preference model. We term this approach Nash learning from human feedback (NLHF). In the context of a tabular policy representation, we present a novel algorithmic solution, Nash-MD, founded on the principles of mirror descent. This algorithm produces a sequence of policies, with the last iteration converging to the regularized Nash equilibrium. Additionally, we explore parametric representations of policies and introduce gradient descent algorithms for deep-learning architectures. We illustrate the effectiveness of our approach by presenting experimental results on a text summarization task. We believe NLHF offers a compelling avenue for fine-tuning LLMs and enhancing the alignment of LLMs with human preferences.
2024-04-30
ICML.cc/2024/Conference (spotlight)
doi.org
proceedings.mlr.press
Nilearn and Big Data Facilitates Transdiagnostic Brain Biomarkers
Hao-Ting Wang
Natasha Clarke
Quentin Dessain
Fraçois Paugam
Lune P Bellec
2024-04-30
Biological Psychiatry (published)
doi.org
Performance of generative pre-trained transformers (GPTs) in Certification Examination of the College of Family Physicians of Canada
Mehdi Mousavi
Shabnam Shafiee
Jason M Harley
Jackie Chi Kit Cheung
Samira Abbasgholizadeh Rahimi
The application of large language models such as generative pre-trained transformers (GPTs) has been promising in medical education, and its… (see more) performance has been tested for different medical exams. This study aims to assess the performance of GPTs in responding to a set of sample questions of short-answer management problems (SAMPs) from the certification exam of the College of Family Physicians of Canada (CFPC). Between August 8th and 25th, 2023, we used GPT-3.5 and GPT-4 in five rounds to answer a sample of 77 SAMPs questions from the CFPC website. Two independent certified family physician reviewers scored AI-generated responses twice: first, according to the CFPC answer key (ie, CFPC score), and second, based on their knowledge and other references (ie, Reviews’ score). An ordinal logistic generalised estimating equations (GEE) model was applied to analyse repeated measures across the five rounds. According to the CFPC answer key, 607 (73.6%) lines of answers by GPT-3.5 and 691 (81%) by GPT-4 were deemed accurate. Reviewer’s scoring suggested that about 84% of the lines of answers provided by GPT-3.5 and 93% of GPT-4 were correct. The GEE analysis confirmed that over five rounds, the likelihood of achieving a higher CFPC Score Percentage for GPT-4 was 2.31 times more than GPT-3.5 (OR: 2.31; 95% CI: 1.53 to 3.47; p0.001). Similarly, the Reviewers’ Score percentage for responses provided by GPT-4 over 5 rounds were 2.23 times more likely to exceed th
2024-04-30
Family Medicine and Community Health (published)
doi.org
Position: Application-Driven Innovation in Machine Learning
David Rolnick
Alán Aspuru-Guzik
Sara Beery
Bistra Dilkina
Priya L. Donti
Marzyeh Ghassemi
Hannah Kerner
Claire Monteleoni
Esther Rolf
Milind Tambe
Adam White
2024-04-30
ICML.cc/2024/Conference (poster)
proceedings.mlr.press
proceedings.mlr.press