The rapid expansion in the size of new datasets has created a need for fast and efficient parameter-learning techniques.Compressive learning is a framework that enables efficient processing by using random, nonlinear features to project large-scale databases onto compact, information-preserving representations whose dimensionality is independent of the number of samples and can be easily stored, transferred, and processed.These database-level summaries are then used to decode parameters of interest from the underlying data distribution without requiring access to the original samples, offering an efficient and privacy-friendly learning framework.However, both the encoding and decoding techniques are typically randomized and data-independent, failing to exploit the underlying structure of the data.In this work, we propose a framework that meta-learns both the encoding and decoding stages of compressive learning methods by using neural networks that provide faster and more accurate systems than the current state-of-the-art approaches.To demonstrate the potential of the presented Compressive Meta-Learning framework, we explore multiple applications-including neural network-based compressive PCA, compressive ridge regression, compressive k-means, and autoencoders.

Training deep learning models and performing hyperparameter tuning can be computationally demanding and time-consuming. Meanwhile, traditional machine learning methods like gradient-boosting algorithms remain the preferred choice for most tabular data applications, while neural network alternatives require extensive hyperparameter tuning or work only in toy datasets under limited settings. In this paper, we introduce HyperFast, a meta-trained hypernetwork designed for instant classification of tabular data in a single forward pass. HyperFast generates a task-specific neural network tailored to an unseen dataset that can be directly used for classification inference, removing the need for training a model. We report extensive experiments with OpenML and genomic data, comparing HyperFast to competing tabular data neural networks, traditional ML methods, AutoML systems, and boosting machines. HyperFast shows highly competitive results, while being significantly faster. Additionally, our approach demonstrates robust adaptability across a variety of classification tasks with little to no fine-tuning, positioning HyperFast as a strong solution for numerous applications and rapid model deployment. HyperFast introduces a promising paradigm for fast classification, with the potential to substantially decrease the computational burden of deep learning. Our code, which offers a scikit-learn-like interface, along with the trained HyperFast model, can be found at https://github.com/AI-sandbox/HyperFast.

Large-scale and increasingly diverse datasets power modern genomic studies, yet robust data integration and homogenization across varying sources remains a challenge. The multiplicity of file formats and the computational requirements imposed by large genomic datasets make it difficult to deal with multiple data sources. Furthermore, there is a lack of open-source customizable tools to merge genomic databases while providing quality control functionalities. To fill this gap, we present MergeGenome, a machine learning-based method designed to integrate DNA sequences from multiple variant call format (VCF) files while maintaining data quality. By leveraging pre-existing VCF manipulation and imputation software, MergeGenome provides a robust pipeline of comprehensive steps to standardize nomenclature, remove ambiguities, correct strand alignment, eliminate mismatches, impute missing positions, and filter and correct erroneous variants with machine learning, among other functionalities. We demonstrate MergeGenome’s ability to obtain a high-quality combined dataset by merging two databases containing dog DNA and effectively detecting and correcting imputation errors. Finally, we show that using the homogenized dataset provides a boost in phenotype prediction performance.

Precision medicine relies on the ability to identify associations between genomic data and its phenotypic expression in order to provide personalized predictions. Phenotype prediction using statistical models trained on large-scale genomic and phenotypic data is a critical research area at the intersection of machine learning and genomics. Current genotype-to-phenotype models, such as polygenic risk scores, only account for linear relationships, and the use of nonlinear methods is still partially unexplored. In this work, we evaluate the prediction accuracy and scalability of nine nonlinear decision tree-based algorithms, including ensembling and boosting mechanisms, and compare them to linear prediction models. We assess the prediction performance for 24 anthropometric and disease-related phenotypes present in the UK Biobank. By using random feature selection, we explore how accuracy and computational time vary for each method as a function of the number of genetic variants selected. Our results show that tree-based methods, especially gradientboosted trees, can offer superior predictions with computational times comparable to those of linear methods. Thus, models able to capture nonlinear relationships between genotypes and phenotypes merit consideration for integration in upcoming computational systems for personalized medicine.

Feature spaces in the deep layers of convolutional neural networks (CNNs) are often very high-dimensional and difficult to inter-pret. However, convolutional layers consist of multiple channels that are activated by different types of inputs, which suggests that more insights may be gained by studying the channels and how they relate to each other. In this paper, we first analyze theoretically channel-wise non-negative kernel (CW-NNK) regression graphs, which allow us to quantify the overlap between channels and, indirectly, the intrinsic dimension of the data representation manifold. We find that redundancy between channels is significant and varies with the layer depth and the level of regularization during training. Additionally, we observe that there is a correlation between channel overlap in the last convolutional layer and generalization performance. Our experimental results demonstrate that these techniques can lead to a better understanding of deep representations.