Le traitement du langage naturel à l'ère de l'IA générative
Rejoignez-nous à Mila en octobre pour un atelier de trois jour visant à explorer le potentiel de transformation des technologies langagières et leurs implications pour la société.
Ce programme est conçu pour fournir aux professionnel·le·s travaillant dans le domaine de la politique une compréhension fondamentale de la technologie de l'IA.
Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
Publications
Application-Driven Innovation in Machine Learning
David Rolnick
Alan Aspuru-Guzik
Sara Beery
Bistra N. Dilkina
Priya L. Donti
Marzyeh Ghassemi
Hannah Kerner
Claire Monteleoni
Esther Rolf
Milind Tambe
Adam White
As applications of machine learning proliferate, innovative algorithms inspired by specific real-world challenges have become increasingly i… (voir plus)mportant. Such work offers the potential for significant impact not merely in domains of application but also in machine learning itself. In this paper, we describe the paradigm of application-driven research in machine learning, contrasting it with the more standard paradigm of methods-driven research. We illustrate the benefits of application-driven machine learning and how this approach can productively synergize with methods-driven work. Despite these benefits, we find that reviewing, hiring, and teaching practices in machine learning often hold back application-driven innovation. We outline how these processes may be improved.
Predicting Species Occurrence Patterns from Partial Observations
Hager Radi
Mélisande Teng
David Rolnick
To address the interlinked biodiversity and climate crises, we need an understanding of where species occur and how these patterns are chang… (voir plus)ing. However, observational data on most species remains very limited, and the amount of data available varies greatly between taxonomic groups. We introduce the problem of predicting species occurrence patterns given (a) satellite imagery, and (b) known information on the occurrence of other species. To evaluate algorithms on this task, we introduce SatButterfly, a dataset of satellite images, environmental data and observational data for butterflies, which is designed to pair with the existing SatBird dataset of bird observational data. To address this task, we propose a general model, R-Tran, for predicting species occurrence patterns that enables the use of partial observational data wherever found. We find that R-Tran outperforms other methods in predicting species encounter rates with partial information both within a taxon (birds) and across taxa (birds and butterflies). Our approach opens new perspectives to leveraging insights from species with abundant data to other species with scarce data, by modelling the ecosystems in which they co-occur.
The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixe… (voir plus)d language) in a single utterance. This has resulted a formidable challenge for the computational models due to the scarcity of annotated data and presence of noise. A potential solution to mitigate the data scarcity problem in low-resource setup is to leverage existing data in resource-rich language through translation. In this paper, we tackle the problem of code-mixed (Hinglish and Bengalish) to English machine translation. First, we synthetically develop HINMIX, a parallel corpus of Hinglish to English, with ~4.2M sentence pairs. Subsequently, we propose RCMT, a robust perturbation based joint-training model that learns to handle noise in the real-world code-mixed text by parameter sharing across clean and noisy words. Further, we show the adaptability of RCMT in a zero-shot setup for Bengalish to English translation. Our evaluation and comprehensive analyses qualitatively and quantitatively demonstrate the superiority of RCMT over state-of-the-art code-mixed and robust translation methods.
Feature visualization is one of the most popular techniques used to interpret the internal behavior of individual units of trained deep neur… (voir plus)al networks. Based on activation maximization, they consist of finding synthetic or natural inputs that maximize neuron activations. This paper introduces an optimization framework that aims to deceive feature visualization through adversarial model manipulation. It consists of finetuning a pre-trained model with a specifically introduced loss that aims to maintain model performance, while also significantly changing feature visualization. We provide evidence of the success of this manipulation on several pre-trained models for the classification task with ImageNet.
2024-03-24
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
8 years after the visual question answering (VQA) task was proposed, accuracy remains the primary metric for automatic evaluation. VQA Accur… (voir plus)acy has been effective so far in the IID evaluation setting. However, our community is undergoing a shift towards open-ended generative models and OOD evaluation. In this new paradigm, the existing VQA Accuracy metric is overly stringent and underestimates the performance of VQA systems. Thus, there is a need to develop more robust automatic VQA metrics that serve as a proxy for human judgment. In this work, we propose to leverage the in-context learning capabilities of instruction-tuned large language models (LLMs) to build a better VQA metric. We formulate VQA evaluation as an answer-rating task where the LLM is instructed to score the accuracy of a candidate answer given a set of reference answers. We demonstrate the proposed metric better correlates with human judgment compared to existing metrics across several VQA models and benchmarks. We hope wide adoption of our metric will contribute to better estimating the research progress on the VQA task. We plan to release the evaluation code and collected human judgments.
2024-03-24
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
The aftermath of the Covid-19 pandemic saw more severe outcomes for racial minority groups and economically-deprived communities. Such dispa… (voir plus)rities can be explained by several factors, including unequal access to healthcare, as well as the inability of low income groups to reduce their mobility due to work or social obligations. Moreover, senior citizens were found to be more susceptible to severe symptoms, largely due to age-related health reasons. Adapting vaccine distribution strategies to consider a range of demographics is therefore essential to address these disparities. In this study, we propose a novel approach that utilizes influence maximization (IM) on mobility networks to develop vaccination strategies which incorporate demographic fairness. By considering factors such as race, social status, age, and associated risk factors, we aim to optimize vaccine distribution to achieve various fairness definitions for one or more protected attributes at a time. Through extensive experiments conducted on Covid-19 spread in three major metropolitan areas across the United States, we demonstrate the effectiveness of our proposed approach in reducing disease transmission and promoting fairness in vaccination distribution.
2024-03-24
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
Human trafficking (HT) for forced sexual exploitation, often described as modern-day slavery, is a pervasive problem that affects millions o… (voir plus)f people worldwide. Perpetrators of this crime post advertisements (ads) on behalf of their victims on adult service websites (ASW). These websites typically contain hundreds of thousands of ads including those posted by independent escorts, massage parlor agencies and spammers (fake ads). Detecting suspicious activity in these ads is difficult and developing data-driven methods is challenging due to the hard-to-label, complex and sensitive nature of the data.
In this paper, we propose T-Net, which unlike previous solutions, formulates this problem as weakly supervised classification. Since it takes several months to years to investigate a case and obtain a single definitive label, we design domain-specific signals or indicators that provide weak labels. T-Net also looks into connections between ads and models the problem as a graph learning task instead of classifying ads independently. We show that T-Net outperforms all baselines on a real-world dataset of ads by 7% average weighted F1 score. Given that this data contains personally identifiable information, we also present a realistic data generator and provide the first publicly available dataset in this domain which may be leveraged by the wider research community.
2024-03-24
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
Chimeric Antigen Receptor (CAR) T cell immunotherapy represents a breakthrough in the treatment of hematological malignancies. However, the … (voir plus)rarity of cell surface protein targets that are specific to cancerous but not vital healthy tissue has hindered its broad application to solid tumor treatment. While new logic-gated CAR designs have shown reduced toxicity against healthy tissues, the generalizability of such approaches across tumors remains unclear. Here, we harness a universal characteristic of endogenous T cell receptors (TCRs), their ability to discriminate between self and non-self ligands through inhibition of response against self (weak) antigens, to develop a broadly applicable method of enhancing immunotherapeutic precision. We hypothesized that this discriminatory mechanism, known as antagonism, would apply across receptors, allowing for a transfer of specificity from TCRs onto CARs. We therefore systematically mapped out the responses of CAR T cells to joint TCR and CAR stimulations. We first engineered murine T cells with an ovalbumin-specific TCR to express a CAR targeting murine CD19 and discovered that the expression of a strong TCR antigen on CD19+ leukemia enhanced CAR T killing. Importantly though, the presence of a weak TCR antigen antagonized CAR T responses, assessed by in vitro multiplexed dynamic profiling as well as in vivo cytotoxicity. We developed a mathematical model based on cross-receptor inhibitory coupling that accurately predicted the extent of TCR/CAR antagonism across a wide range of immunological settings. This model was validated in a CD19+ B16 mouse melanoma model showing that TCR/CAR antagonism decreased the infiltration of a tumor-reactive T cell cluster, while TCR/CAR agonism enhanced infiltration of this T cell cluster. We then applied our quantitative knowledge of TCR/CAR crosstalk to design an Antagonism-Enforced Braking System (AEBS) for CAR T cell therapy. This was assessed in a model system using a CAR targeting the tyrosine-protein kinase erbB-2 (HER2) together with a hedgehog acyltransferase (HHAT) peptide-specific TCR that binds strongly to mutated tumor neoantigen while retaining weak affinity for the wild-type self-antigen on healthy tissue. We established a humanized in vivo model of CAR T function and found that AEBS CAR T cells maintained high anti-tumor activity against a human lung adenocarcinoma (PC9) but notably, their anti-tissue cytotoxicity against human bronchial epithelial cells (BEAS-2B) was minimized. AEBS CAR T cells therefore sharpen the discriminatory power of synthetic anti-tumor lymphocytes. Our work highlights a novel mechanism by which TCRs can enforce CAR T cell specificity, with practical implications for the rational design of future anti-leukemia immunotherapies.
Citation Format: Taisuke Kondo, François X. Bourassa, Sooraj Achar, Justyn DuSold, Pablo Cespedes, Madison Wahlsten, Audun Kvalvaag, Guillaume Gaud, Paul Love, Michael Dustin, Gregoire Altan-Bonnet, Paul François, Naomi Taylor. Antagonism-enforced braking system to enhance CAR T cell therapeutic specificity [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6324.