Related papers: MAFS: Multi-head Attention Feature Selection for H…
Machine learning models depend critically on feature quality, yet useful features are often scattered across multiple relational tables. Feature augmentation enriches a base table by discovering and integrating features from related tables…
High-dimensional and sparse (HiDS) matrices are omnipresent in a variety of big data-related applications. Latent factor analysis (LFA) is a typical representation learning method that extracts useful yet latent knowledge from HiDS matrices…
Federated Learning (FL) faces major challenges regarding communication overhead and model privacy when training large language models (LLMs), especially in healthcare applications. To address these, we introduce Selective Attention…
Feature selection is a crucial step in large-scale industrial machine learning systems, directly affecting model accuracy, efficiency, and maintainability. Traditional feature selection methods rely on labeled data and statistical…
Modern biomedical data mining requires feature selection methods that can (1) be applied to large scale feature spaces (e.g. `omics' data), (2) function in noisy problems, (3) detect complex patterns of association (e.g. gene-gene…
High dynamic range (HDR) imaging enables to immortalize natural scenes similar to the way that they are perceived by human observers. With regular low dynamic range (LDR) capture/display devices, significant details may not be preserved in…
Data-centric AI encourages the need of cleaning and understanding of data in order to achieve trustworthy AI. Existing technologies, such as AutoML, make it easier to design and train models automatically, but there is a lack of a similar…
Regression-based methods have shown high efficiency and effectiveness for multi-view human mesh recovery. The key components of a typical regressor lie in the feature extraction of input views and the fusion of multi-view features. In this…
Emotions play a central role in the social life of every human being, and their study, which represents a multidisciplinary subject, embraces a great variety of research fields. Especially concerning the latter, the analysis of facial…
In this paper, we propose a new deep feature selection method based on deep architecture. Our method uses stacked auto-encoders for feature representation in higher-level abstraction. We developed and applied a novel feature learning…
Accurate and interpretable survival analysis remains a core challenge in oncology. With growing multimodal data and the clinical need for transparent models to support validation and trust, this challenge increases in complexity. We propose…
Automated histopathological image analysis offers exciting opportunities for the early diagnosis of several medical conditions including cancer. There are however stiff practical challenges: 1.) discriminative features from such images for…
Instance segmentation is an important task for biomedical and biological image analysis. Due to the complicated background components, the high variability of object appearances, numerous overlapping objects, and ambiguous object…
The self-attention mechanism, now central to deep learning architectures such as Transformers, is a modern instance of a more general computational principle: learning and using pairwise affinity matrices to control how information flows…
The primary objective of human activity recognition (HAR) is to infer ongoing human actions from sensor data, a task that finds broad applications in health monitoring, safety protection, and sports analysis. Despite proliferating research,…
In recent years, deep learning models have demonstrated remarkable success in various domains, such as computer vision, natural language processing, and speech recognition. However, the generalization capabilities of these models can be…
Factorization Machines (FMs) are a supervised learning approach that enhances the linear regression model by incorporating the second-order feature interactions. Despite effectiveness, FM can be hindered by its modelling of all feature…
Physiological signals are inherently heterogeneous: they are collected under diverse acquisition setups, differ in the number and type of modalities and channels, varying in quality, reliability, and relevance across tasks. This variability…
Large Language Models(LLMs) excel in general tasks but struggle in specialized domains like healthcare due to limited domain-specific knowledge.Supervised Fine-Tuning(SFT) data construction for domain adaptation often relies on heuristic…
We propose the Multi-Head Density Adaptive Attention Mechanism (DAAM), a novel probabilistic attention framework that can be used for Parameter-Efficient Fine-tuning (PEFT), and the Density Adaptive Transformer (DAT), designed to enhance…