Publications

Adaptive Group Robust Ensemble Knowledge Distillation

Patrik Joslin Kenfack

Ulrich Matchi Aïvodji

S Ebrahimi Kahou

Neural networks can learn spurious correlations in the data, often leading to performance disparity for underrepresented subgroups. Studies … (voir plus)have demonstrated that the disparity is amplified when knowledge is distilled from a complex teacher model to a relatively"simple"student model. Prior work has shown that ensemble deep learning methods can improve the performance of the worst-case subgroups; however, it is unclear if this advantage carries over when distilling knowledge from an ensemble of teachers, especially when the teacher models are debiased. This study demonstrates that traditional ensemble knowledge distillation can significantly drop the performance of the worst-case subgroups in the distilled student model even when the teacher models are debiased. To overcome this, we propose Adaptive Group Robust Ensemble Knowledge Distillation (AGRE-KD), a simple ensembling strategy to ensure that the student model receives knowledge beneficial for unknown underrepresented subgroups. Leveraging an additional biased model, our method selectively chooses teachers whose knowledge would better improve the worst-performing subgroups by upweighting the teachers with gradient directions deviating from the biased model. Our experiments on several datasets demonstrate the superiority of the proposed ensemble distillation technique and show that it can even outperform classic model ensembles based on majority voting.

2024-12-31

Trans. Mach. Learn. Res. (publié)

doi.org

openreview.net

Advancements in Affective and Behavior Analysis: The 8th ABAW Workshop and Competition

Dimitrios Kollias

Panagiotis Tzirakis

Alan Cowen

Stefanos Zafeiriou

Irene Kotsia

Eric Granger

Marco Pedersoli

Simon Bacon

Alice Baird

Chris Gagne

Chunchang Shao

Guanyu Hu

Soufiane Belharbi

Muhammad Haseeb Aslam

2024-12-31

CVPR Workshops (publié)

doi.org

Advocacy for Children With Surgical Diseases in Nigeria: National Policy Status, Gaps, and Solutions

Justina O. Seyi-Olajide

Ayla Gerk

Elena Guadagno

Adesoji Ademuyiwa

Emmanuel A. Ameh

Dan Poenaru

2024-12-31

Journal of Pediatric Surgery (publié)

doi.org

AFRIDOC-MT: Document-level MT Corpus for African Languages

Jesujoba Oluwadara Alabi

Israel Abebe Azime

Miaoran Zhang

Cristina España-Bonet

Rachel Bawden

Dawei Zhu

David Ifeoluwa Adelani

Clement Odoje

Idris Akinade

Iffat Maab

Davis David

Shamsuddeen Hassan Muhammad

Neo Putini

David O. Ademuyiwa

Andrew Caines

Dietrich Klakow

This paper introduces AFRIDOC-MT, a document-level multi-parallel translation dataset covering English and five African languages: Amharic, … (voir plus)Hausa, Swahili, Yor\`ub\'a, and Zulu. The dataset comprises 334 health and 271 information technology news documents, all human-translated from English to these languages. We conduct document-level translation benchmark experiments by evaluating neural machine translation (NMT) models and large language models (LLMs) for translations between English and these languages, at both the sentence and pseudo-document levels. These outputs are realigned to form complete documents for evaluation. Our results indicate that NLLB-200 achieved the best average performance among the standard NMT models, while GPT-4o outperformed general-purpose LLMs. Fine-tuning selected models led to substantial performance gains, but models trained on sentences struggled to generalize effectively to longer documents. Furthermore, our analysis reveals that some LLMs exhibit issues such as under-generation, repetition of words or phrases, and off-target translations, especially for African languages.

2024-12-31

EMNLP (publié)

doi.org

arxiv.org

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

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