Publications

Anatomically-Focused Patches for Lightweight and Explainable Knee OA Grading
Tien-en Chang
Hervé Lombaert
2024-12-31
ShapeMI@MICCAI (publié)
doi.org
Anticancer Monotherapy and Polytherapy Drug Response Prediction Using Deep Learning: Guidelines and Best Practices
Amin Emad
David Earl Hostallero
2024-12-31
Methods in Molecular Biology (inconnu)
doi.org
Anti-patterns and Code Smells for Multi-language Systems
Mouna Abidi
Manel Grichi
Foutse Khomh
Yann‐Gaël Guéhéneuc
2024-12-31
Transactions on Pattern Languages of Programming (publié)
doi.org
Attention as a Hypernetwork
Simon Schug
Seijin Kobayashi
Yassir Akram
João Sacramento
Razvan Pascanu
Transformers can under some circumstances generalize to novel problem instances whose constituent parts might have been encountered during t… (voir plus)raining, but whose compositions have not. What mechanisms underlie this ability for compositional generalization? By reformulating multi-head attention as a hypernetwork, we reveal that a composable, low-dimensional latent code specifies key-query specific operations. We find empirically that this latent code is predictive of the subtasks the network performs on unseen task compositions, revealing that latent codes acquired during training are reused to solve unseen problem instances. To further examine the hypothesis that the intrinsic hypernetwork of multi-head attention supports compositional generalization, we ablate whether making the hypernetwork-generated linear value network nonlinear strengthens compositionality. We find that this modification improves compositional generalization on abstract reasoning tasks. In particular, we introduce a symbolic version of the Raven's Progressive Matrices human intelligence test, which gives us precise control over the problem compositions encountered during training and evaluation. We demonstrate on this task how scaling model size and data enables compositional generalization in transformers and gives rise to a functionally structured latent space.
2024-12-31
ICLR (publié)
doi.org
arxiv.org
Audio Prototypical Network For Controllable Music Recommendation
Fırat Öncel
Emiliano Penaloza
Haolun Wu
Shubham Gupta
Mirco Ravanelli
Laurent Charlin
Cem Subakan
Traditional recommendation systems represent user preferences in dense representations obtained through black-box encoder models. While thes… (voir plus)e models often provide strong recommendation performance, they lack interpretability for users, leaving users unable to understand or control the system's modeling of their preferences. This limitation is especially challenging in music recommendation, where user preferences are highly personal and often evolve based on nuanced qualities like mood, genre, tempo, or instrumentation. In this paper, we propose an audio prototypical network for controllable music recommendation. This network expresses user preferences in terms of prototypes representative of semantically meaningful features pertaining to musical qualities. We show that the model obtains competitive recommendation performance compared to popular baseline models while also providing interpretable and controllable user profiles.
2024-12-31
MLSP (publié)
doi.org
openreview.net
AugmenToxic: Leveraging Reinforcement Learning to Optimize LLM Instruction Fine-Tuning for Data Augmentation to Enhance Toxicity Detection.
Arezo Bodaghi
Benjamin C. M. Fung
Ketra A. Schmitt
Addressing the challenge of toxic language in online discussions is crucial for the development of effective toxicity detection models. This… (voir plus) pioneering work focuses on addressing imbalanced datasets in toxicity detection by introducing a novel approach to augment toxic language data. We create a balanced dataset by instructing fine-tuning of Large Language Models (LLMs) using Reinforcement Learning with Human Feedback (RLHF). Recognizing the challenges in collecting sufficient toxic samples from social media platforms for building a balanced dataset, our methodology involves sentence-level text data augmentation through paraphrasing existing samples using optimized generative LLMs. Leveraging generative LLM, we utilize the Proximal Policy Optimizer (PPO) as the RL algorithm to fine-tune the model further and align it with human feedback. In other words, we start by fine-tuning a LLM using an instruction dataset, specifically tailored for the task of paraphrasing while maintaining semantic consistency. Next, we apply PPO and a reward function, to further fine-tune (optimize) the instruction-tuned LLM. This RL process guides the model in generating toxic responses. We utilize the Google Perspective API as a toxicity evaluator to assess generated responses and assign rewards/penalties accordingly. This approach guides LLMs through PPO and the reward function, transforming minority class samples into augmented versions. The primary goal of our methodology is to create a balanced and diverse dataset to enhance the accuracy and performance of classifiers in identifying instances from the minority class. Utilizing two publicly available toxic datasets, we compared various techniques with our proposed method for generating toxic samples, demonstrating that our approach outperforms all others in producing a higher number of toxic samples. Starting with an initial 16,225 toxic prompts, our method successfully generated 122,951 toxic samples with a toxicity score exceeding 30%. Subsequently, we developed various classifiers using the generated balanced datasets and applied a cost-sensitive learning approach to the original imbalanced dataset. The findings highlight the superior performance of classifiers trained on data generated using our proposed method. These results highlight the importance of employing RL and a data-agnostic model as a reward mechanism for augmenting toxic data, thereby enhancing the robustness of toxicity detection models.
2024-12-31
ACM Transactions on the Web (publié)
doi.org
AURA: A Multi-modal Medical Agent for Understanding, Reasoning and Annotation
Nima Fathi
Amar Kumar
Tal Arbel
2024-12-31
Agentic AI/CREATE/Clinical MLLMs@MICCAI (publié)
doi.org
Automated UML Visualization of Software Ecosystems: Tracking Versions, Dependencies, and Security Updates
Vanessa Kan
M. P. Lnu
Solomon Berhe
C. El Kari
Marc Maynard
Foutse Khomh
2024-12-31
ANT/EDI40 (publié)
doi.org
Balancing Profit and Fairness in Risk-Based Pricing Markets
Jesse Thibodeau
Hadi Nekoei
Afaf Taïk
Janarthanan Rajendran
Golnoosh Farnadi
Dynamic, risk-based pricing can systematically exclude vulnerable consumer groups from essential resources such as health insurance and cons… (voir plus)umer credit. We show that a regulator can realign private incentives with social objectives through a learned, interpretable tax schedule. First, we provide a formal proposition that bounding each firm's \emph{local} demographic gap implicitly bounds the \emph{global} opt-out disparity, motivating firm-level penalties. Building on this insight we introduce \texttt{MarketSim} -- an open-source, scalable simulator of heterogeneous consumers and profit-maximizing firms -- and train a reinforcement learning (RL) social planner (SP) that selects a bracketed fairness-tax while remaining close to a simple linear prior via an
2024-12-31
arXiv (prépublication)
doi.org
arxiv.org
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
Yunzhen Feng
Elvis Dohmatob
Pu Yang
Francois Charton
Julia Kempe
Large Language Models (LLM) are increasingly trained on data generated by other LLM, either because generated text and images become part of… (voir plus) the pre-training corpus, or because synthetized data is used as a replacement for expensive human-annotation. This raises concerns about \emph{model collapse}, a drop in model performance when their training sets include generated data. Considering that it is easier for both humans and machines to tell between good and bad examples than to generate high-quality samples, we investigate the use of verification on synthesized data to prevent model collapse. We provide a theoretical characterization using Gaussian mixtures, linear classifiers, and linear verifiers to derive conditions with measurable proxies to assess whether the verifier can effectively select synthesized data that leads to optimal performance. We experiment with two practical tasks -- computing matrix eigenvalues with transformers and news summarization with LLMs -- which both exhibit model collapse when trained on generated data, and show that verifiers, even imperfect ones, can indeed be harnessed to prevent model collapse and that our proposed proxy measure strongly correlates with performance.
2024-12-31
ICLR (publié)
doi.org
openreview.net
Bidirectional Information Flow (BIF) -- A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization
Juan D. Guerra
Thomas Garbay
Guillaume Lajoie
Marco Bonizzato
Hierarchical Gaussian Process (H-GP) models divide problems into different subtasks, allowing for different models to address each part, mak… (voir plus)ing them well-suited for problems with inherent hierarchical structure. However, typical H-GP models do not fully take advantage of this structure, only sending information up or down the hierarchy. This one-way coupling limits sample efficiency and slows convergence. We propose Bidirectional Information Flow (BIF), an efficient H-GP framework that establishes bidirectional information exchange between parent and child models in H-GPs for online training. BIF retains the modular structure of hierarchical models - the parent combines subtask knowledge from children GPs - while introducing top-down feedback to continually refine children models during online learning. This mutual exchange improves sample efficiency, enables robust training, and allows modular reuse of learned subtask models. BIF outperforms conventional H-GP Bayesian Optimization methods, achieving up to 4x and 3x higher
2024-12-31
arXiv (prépublication)
doi.org
arxiv.org
A Biodiversity Observation Network to support conservation action and mainstream knowledge in Canada
Andrew Gonzalez
Mary I. O'Connor
Amanda E. Bates
Kyle Bobiwash
A. Cole Burton
Paul van Dam-Bates
Isaac Eckert
Dominique Gravel
C. Julián Idrobo
Laura Pollock
Andrew D.F. Simon
Margaret A. Slein
Péter Sólymos
Brian M. Starzomski
Jennifer Sunday
Eden Tekwa
Canada has begun an ambitious project to build an observing system to monitor the changing state of its biodiversity and ecosystems. A Canad… (voir plus)a-wide Biodiversity Observation Network (CAN BON) can support the measurement, mapping, and modelling of biodiversity change—the losses and gains in the diversity of plant, animal, and microbial life—and ecosystem services. This initiative responds to eight challenges presently constraining Canada's capacity to deliver timely and robust knowledge to achieve its biodiversity goals. CAN BON is conceived as a network connecting diverse organizations to support sustained biodiversity monitoring by collaboration among universities, museums, governments, industries, NGOs, community groups, and Indigenous organizations. This inclusive network will “mobilize monitoring data” to (1) combine observation and computing infrastructures and traditional knowledge to track and understand biodiversity losses and gains across the country; and (2) link the accumulated data and knowledge to models to inform the detection and attribution of biodiversity change needed to support biodiversity policy with forecasts from local to national levels. We expect that CAN BON will foster the mainstreaming of biodiversity data and knowledge into other sectors of the economy and society, and thereby support the technical and social innovation in Canada's transition to a nature-positive future.
2024-12-31
Formal Aspects of Component Software (publié)
doi.org