Publications

Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers
Umberto Cappellazzo
Daniele Falavigna
Alessio Brutti
Mirco Ravanaelli
The common modus operandi of fine-tuning large pre-trained Transformer models entails the adaptation of all their parameters (i.e., full fin… (voir plus)e-tuning). While achieving striking results on multiple tasks, this approach becomes unfeasible as the model size and the number of downstream tasks increase. In natural language processing and computer vision, parameter-efficient approaches like prompt-tuning and adapters have emerged as solid alternatives by fine-tuning only a small number of extra parameters, without sacrificing performance accuracy. For audio classification tasks, the Audio Spectrogram Transformer model shows impressive results. However, surprisingly, how to efficiently adapt it to several downstream tasks has not been tackled before. In this paper, we bridge this gap and present a detailed investigation of common parameter-efficient methods, revealing that adapters and LoRA consistently outperform the other methods across four benchmarks. Whereas adapters prove to be more efficient in few-shot learning settings, LoRA turns out to scale better as we increase the number of learnable parameters. We finally carry out ablation studies to find the best configuration for adapters and LoRA.
2023-12-31
MLSP (publié)
doi.org
arxiv.org
Performance reserves in brain-imaging-based phenotype prediction
Marc-Andre Schulz
Danilo Bzdok
Stefan Haufe
John-Dylan Haynes
Kerstin Ritter
This study examines the impact of sample size on predicting cognitive and mental health phenotypes from brain imaging via machine learning. … (voir plus)Our analysis shows a 3- to 9-fold improvement in prediction performance when sample size increases from 1,000 to 1 M participants. However, despite this increase, the data suggest that prediction accuracy remains worryingly low and far from fully exploiting the predictive potential of brain imaging data. Additionally, we find that integrating multiple imaging modalities boosts prediction accuracy, often equivalent to doubling the sample size. Interestingly, the most informative imaging modality often varied with increasing sample size, emphasizing the need to consider multiple modalities. Despite significant performance reserves for phenotype prediction, achieving substantial improvements may necessitate prohibitively large sample sizes, thus casting doubt on the practical or clinical utility of machine learning in some areas of neuroimaging.
2023-12-31
Cell Reports (publié)
doi.org
PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design
Alexandre Duval
Victor Schmidt
Santiago Miret
Yoshua Bengio
Alex Hernández-García
David Rolnick
Mitigating the climate crisis requires a rapid transition towards lower-carbon energy. Catalyst materials play a crucial role in the electro… (voir plus)chemical reactions involved in numerous industrial processes key to this transition, such as renewable energy storage and electrofuel synthesis. To reduce the energy spent on such activities, we must quickly discover more efficient catalysts to drive electrochemical reactions. Machine learning (ML) holds the potential to efficiently model materials properties from large amounts of data, accelerating electrocatalyst design. The Open Catalyst Project OC20 dataset was constructed to that end. However, ML models trained on OC20 are still neither scalable nor accurate enough for practical applications. In this paper, we propose task-specific innovations applicable to most architectures, enhancing both computational efficiency and accuracy. This includes improvements in (1) the graph creation step, (2) atom representations, (3) the energy prediction head, and (4) the force prediction head. We describe these contributions, referred to as PhAST, and evaluate them thoroughly on multiple architectures. Overall, PhAST improves energy MAE by 4 to 42
2023-12-31
Journal of Machine Learning Research (publié)
doi.org
openreview.net
PID Accelerated Temporal Difference Algorithms
Mark Bedaywi
Amin Rakhsha
Amir-massoud Farahmand
Long-horizon tasks, which have a large discount factor, pose a challenge for most conventional reinforcement learning (RL) algorithms. Algor… (voir plus)ithms such as Value Iteration and Temporal Difference (TD) learning have a slow convergence rate and become inefficient in these tasks. When the transition distributions are given, PID VI was recently introduced to accelerate the convergence of Value Iteration using ideas from control theory. Inspired by this, we introduce PID TD Learning and PID Q-Learning algorithms for the RL setting, in which only samples from the environment are available. We give a theoretical analysis of the convergence of PID TD Learning and its acceleration compared to the conventional TD Learning. We also introduce a method for adapting PID gains in the presence of noise and empirically verify its effectiveness.
2023-12-31
RLJ (publié)
doi.org
arxiv.org
Policy Gradient Methods in the Presence of Symmetries and State Abstractions
Prakash Panangaden
Sahand Rezaei-Shoshtari
Rosie Zhao
David Meger
Doina Precup
Reinforcement learning (RL) on high-dimensional and complex problems relies on abstraction for improved efficiency and generalization. In th… (voir plus)is paper, we study abstraction in the continuous-control setting, and extend the definition of Markov decision process (MDP) homomorphisms to the setting of continuous state and action spaces. We derive a policy gradient theorem on the abstract MDP for both stochastic and deterministic policies. Our policy gradient results allow for leveraging approximate symmetries of the environment for policy optimization. Based on these theorems, we propose a family of actor-critic algorithms that are able to learn the policy and the MDP homomorphism map simultaneously, using the lax bisimulation metric. Finally, we introduce a series of environments with continuous symmetries to further demonstrate the ability of our algorithm for action abstraction in the presence of such symmetries. We demonstrate the effectiveness of our method on our environments, as well as on challenging visual control tasks from the DeepMind Control Suite. Our method's ability to utilize MDP homomorphisms for representation learning leads to improved performance, and the visualizations of the latent space clearly demonstrate the structure of the learned abstraction.
2023-12-31
J. Mach. Learn. Res. (publié)
doi.org
arxiv.org
Population Monte Carlo With Normalizing Flow
Soumyasundar Pal
Antonios Valkanas
Mark J. Coates
Adaptive importance sampling (AIS) methods provide a useful alternative to Markov Chain Monte Carlo (MCMC) algorithms for performing inferen… (voir plus)ce of intractable distributions. Population Monte Carlo (PMC) algorithms constitute a family of AIS approaches which adapt the proposal distributions iteratively to improve the approximation of the target distribution. Recent work in this area primarily focuses on ameliorating the proposal adaptation procedure for high-dimensional applications. However, most of the AIS algorithms use simple proposal distributions for sampling, which might be inadequate in exploring target distributions with intricate geometries. In this work, we construct expressive proposal distributions in the AIS framework using normalizing flow, an appealing approach for modeling complex distributions. We use an iterative parameter update rule to enhance the approximation of the target distribution. Numerical experiments show that in high-dimensional settings, the proposed algorithm offers significantly improved performance compared to the existing techniques.
2023-12-31
IEEE Signal Processing Letters (publié)
doi.org
arxiv.org
Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms
Elvis Dopgima Dohmatob
Meyer Scetbon
2023-12-31
International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
Predicting Drug Effects from High-Dimensional, Asymmetric Drug Datasets by Using Graph Neural Networks: A Comprehensive Analysis of Multitarget Drug Effect Prediction
Avishek Bose
Guojing Cong
Graph neural networks (GNNs) have emerged as one of the most effective ML techniques for drug effect prediction from drug molecular graphs. … (voir plus)Despite having immense potential, GNN models lack performance when using datasets that contain high-dimensional, asymmetrically co-occurrent drug effects as targets with complex correlations between them. Training individual learning models for each drug effect and incorporating every prediction result for a wide spectrum of drug effects are impractical. Therefore, an opportunity exists to address this challenge as multitarget prediction problems and predict all drug effects at a time. We developed standard and hybrid GNNs to perform two separate tasks: multiregression for continuous values and multilabel classification for categorical values contained in our datasets. Because multilabel classification makes the target data even more sparse and introduces asymmetric label co-occurrence, learning these models becomes difficult and heavily impacts the GNN's performance. To address these challenges, we propose a new data oversampling technique to improve multilabel classification performances on all the given imbalanced molecular graph datasets. Using the technique, we improve the data imbalance ratio of the drug effects while protecting the datasets' integrity. Finally, we evaluate the multilabel classification performance of the best-performing hybrid GNN model on all the oversampled datasets obtained from the proposed oversampling technique. In all the evaluation metrics (i.e., precision, recall, and F1 score), this model significantly outperforms other ML models, including GNN models when they are trained on the original datasets or oversampled datasets with MLSMOTE, which is a well-known oversampling technique.
2023-12-31
ICMLA (publié)
doi.org
arxiv.org
Probabilistic Dataset Reconstruction from Interpretable Models
Julien Ferry
Ulrich Matchi Aïvodji
Sébastien Gambs
Marie-José Huguet
Mohamed Siala
Interpretability is often pointed out as a key requirement for trustworthy machine learning. However, learning and releasing models that are… (voir plus) inherently interpretable leaks information regarding the underlying training data. As such disclosure may directly conflict with privacy, a precise quantification of the privacy impact of such breach is a fundamental problem. For instance, previous work have shown that the structure of a decision tree can be leveraged to build a probabilistic reconstruction of its training dataset, with the uncertainty of the reconstruction being a relevant metric for the information leak. In this paper, we propose of a novel framework generalizing these probabilistic reconstructions in the sense that it can handle other forms of interpretable models and more generic types of knowledge. In addition, we demonstrate that under realistic assumptions regarding the interpretable models' structure, the uncertainty of the reconstruction can be computed efficiently. Finally, we illustrate the applicability of our approach on both decision trees and rule lists, by comparing the theoretical information leak associated to either exact or heuristic learning algorithms. Our results suggest that optimal interpretable models are often more compact and leak less information regarding their training data than greedily-built ones, for a given accuracy level.
2023-12-31
SaTML (publié)
doi.org
openreview.net
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
Damien Ferbach
Baptiste Goujaud
Gauthier Gidel
Aymeric Dieuleveut
The energy landscape of high-dimensional non-convex optimization problems is crucial to understanding the effectiveness of modern deep neura… (voir plus)l network architectures. Recent works have experimentally shown that two different solutions found after two runs of a stochastic training are often connected by very simple continuous paths (e.g., linear) modulo a permutation of the weights. In this paper, we provide a framework theoretically explaining this empirical observation. Based on convergence rates in Wasserstein distance of empirical measures, we show that, with high probability, two wide enough two-layer neural networks trained with stochastic gradient descent are linearly connected. Additionally, we express upper and lower bounds on the width of each layer of two deep neural networks with independent neuron weights to be linearly connected. Finally, we empirically demonstrate the validity of our approach by showing how the dimension of the support of the weight distribution of neurons, which dictates Wasserstein convergence rates is correlated with linear mode connectivity.
2023-12-31
AISTATS (publié)
doi.org
proceedings.mlr.press
Quantifying learning-style adaptation in effectiveness of LLM teaching
Ruben Weijers
Gabrielle Fidelis de Castilho
Jean-François Godbout
Reihaneh Rabbany
Kellin Pelrine
This preliminary study aims to investigate whether AI, when prompted based on individual learning styles, can effectively improve comprehens… (voir plus)ion and learning experiences in educational settings. It involves tailoring LLMs baseline prompts and comparing the results of a control group receiving standard content and an experimental group receiving learning style-tailored content. Preliminary results suggest that GPT-4 can generate responses aligned with various learning styles, indicating the potential for enhanced engagement and comprehension. However, these results also reveal challenges, including the model’s tendency for sycophantic behavior and variability in responses. Our findings suggest that a more sophisticated prompt engineering approach is required for integrating AI into education (AIEd) to improve educational outcomes.
2023-12-31
PERSONALIZE (publié)
doi.org
Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models
Eva Portelance
Siva Reddy
Timothy J. O'Donnell
Semantic and syntactic bootstrapping posit that children use their prior knowledge of one linguistic domain, say syntactic relations, to hel… (voir plus)p later acquire another, such as the meanings of new words. Empirical results supporting both theories may tempt us to believe that these are different learning strategies, where one may precede the other. Here, we argue that they are instead both contingent on a more general learning strategy for language acquisition: joint learning. Using a series of neural visually-grounded grammar induction models, we demonstrate that both syntactic and semantic bootstrapping effects are strongest when syntax and semantics are learnt simultaneously. Joint learning results in better grammar induction, realistic lexical category learning, and better interpretations of novel sentence and verb meanings. Joint learning makes language acquisition easier for learners by mutually constraining the hypotheses spaces for both syntax and semantics. Studying the dynamics of joint inference over many input sources and modalities represents an important new direction for language modeling and learning research in both cognitive sciences and AI, as it may help us explain how language can be acquired in more constrained learning settings.
2023-12-31
arXiv (prépublication)
doi.org
arxiv.org