Related papers: FeatNavigator: Automatic Feature Augmentation on T…
Computer vision models normally witness degraded performance when deployed in real-world scenarios, due to unexpected changes in inputs that were not accounted for during training. Data augmentation is commonly used to address this issue,…
Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown that augmentation strategies found by search algorithms…
High-order interactive features capture the correlation between different columns and thus are promising to enhance various learning tasks on ubiquitous tabular data. To automate the generation of interactive features, existing works either…
The application of deep learning to build accurate predictive models from functional neuroimaging data is often hindered by limited dataset sizes. Though data augmentation can help mitigate such training obstacles, most data augmentation…
Data augmentation methods enrich datasets with augmented data to improve the performance of neural networks. Recently, automated data augmentation methods have emerged, which automatically design augmentation strategies. Existing work…
Existing feature engineering methods based on large language models (LLMs) have not yet been applied to multi-label learning tasks. They lack the ability to model complex label dependencies and are not specifically adapted to the…
Federated Learning (FL) enables collaborative model training across diverse entities while safeguarding data privacy. However, FL faces challenges such as data heterogeneity and model diversity. The Meta-Federated Learning (Meta-FL)…
Feature quality has an impactful effect on recommendation performance. Thereby, feature selection is a critical process in developing deep learning-based recommender systems. Most existing deep recommender systems, however, focus on…
While Deep Learning has demonstrated impressive results in applications on various data types, it continues to lag behind tree-based methods when applied to tabular data, often referred to as the last "unconquered castle" for neural…
The common pipeline of training deep neural networks consists of several building blocks such as data augmentation and network architecture selection. AutoML is a research field that aims at automatically designing those parts, but most…
Federated Learning (FL) provides a privacy-preserving mechanism for distributed training of machine learning models on networked devices (e.g., mobile devices, IoT edge nodes). It enables Artificial Intelligence (AI) at the edge by creating…
Foundational vision transformer models have shown impressive few shot performance on many vision tasks. This research presents a novel investigation into the application of parameter efficient fine-tuning methods within an active learning…
There are two fundamental problems in applying deep learning/machine learning methods to disease classification tasks, one is the insufficient number and poor quality of training samples; another one is how to effectively fuse multiple…
Augmentations are the key factor in determining the performance of any neural network as they provide a model with a critical edge in boosting its performance. Their ability to boost a model's robustness depends on two factors, viz-a-viz,…
Tabular data remains one of the most prevalent data types across a wide range of real-world applications, yet effective representation learning for this domain poses unique challenges due to its irregular patterns, heterogeneous feature…
Naive Bayes(NB) is one of the essential algorithms in data mining. However, it is rarely used in reality because of the attribute independent assumption. Researchers have proposed many improved NB methods to alleviate this assumption. Among…
Model merging has emerged as a promising approach for multi-task learning (MTL), offering a data-efficient alternative to conventional fine-tuning. However, with the rapid development of the open-source AI ecosystem and the increasing…
This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data…
The success of the application of machine-learning techniques to compilation tasks can be largely attributed to the recent development and advancement of program characterization, a process that numerically or structurally quantifies a…
This paper introduces a novel framework for enhancing Random Forest classifiers by integrating probabilistic feature sampling and hyperparameter tuning via Simulated Annealing. The proposed framework exhibits substantial advancements in…