Related papers: Autostacker: A Compositional Evolutionary Learning…
Artificial intelligence (AI) techniques are widely applied in the life sciences. However, applying innovative AI techniques to understand and deconvolute biological complexity is hindered by the learning curve for life science scientists to…
Evolutionary model merging provides a powerful framework for the automated, training-free composition of LLMs through parameter-space search. However, existing methods predominantly rely on stochastic, hand-crafted operators that overlook…
Automated Machine Learning (AutoML) offers a promising approach to streamline the training of machine learning models. However, existing AutoML frameworks are often limited to unimodal scenarios and require extensive manual configuration.…
Compared to humans, machine learning models generally require significantly more training examples and fail to extrapolate from experience to solve previously unseen challenges. To help close this performance gap, we augment single-task…
Artificial Intelligence (AI) / Machine Learning (ML)-based systems are widely sought-after commercial solutions that can automate and augment core business services. Intelligent systems can improve the quality of services offered and…
Meta reasoning behaviors work as a skeleton to guide large language model (LLM) reasoning, thus help to improve reasoning performance. However, prior researches implement meta reasoning skeleton with manually designed structure, limiting…
Nowadays, deep learning (DL) models being increasingly applied to various fields, people without technical expertise and domain knowledge struggle to find an appropriate model for their task. In this paper, we introduce AutoCl a visual…
Machine Learning (ML) has gained popularity in actuarial research and insurance industrial applications. However, the performance of most ML tasks heavily depends on data preprocessing, model selection, and hyperparameter optimization,…
The increasing adoption of neural networks in learning-augmented systems highlights the importance of model safety and robustness, particularly in safety-critical domains. Despite progress in the formal verification of neural networks,…
In class-incremental learning, a model learns continuously from a sequential data stream in which new classes occur. Existing methods often rely on static architectures that are manually crafted. These methods can be prone to capacity…
We study the AutoML problem of automatically configuring machine learning pipelines by jointly selecting algorithms and their appropriate hyper-parameters for all steps in supervised learning pipelines. This black-box (gradient-free)…
Previous research on EMA data of mental disorders was mainly focused on multivariate regression-based approaches modeling each individual separately. This paper goes a step further towards exploring the use of non-linear interpretable…
On-device machine learning (ML) has become a fundamental component of emerging mobile applications. Adaptive model deployment delivers efficient inference for heterogeneous device capabilities and performance requirements through…
Background. Due to the widespread adoption of Artificial Intelligence (AI) and Machine Learning (ML) for building software applications, companies are struggling to recruit employees with a deep understanding of such technologies. In this…
The design of modern recommender systems relies on understanding which parts of the feature space are relevant for solving a given recommendation task. However, real-world data sets in this domain are often characterized by their large…
We introduce the concept of a Modular Autoencoder (MAE), capable of learning a set of diverse but complementary representations from unlabelled data, that can later be used for supervised tasks. The learning of the representations is…
Automated Machine Learning (AutoML) supports practitioners and researchers with the tedious task of designing machine learning pipelines and has recently achieved substantial success. In this paper, we introduce new AutoML approaches…
Designing optimization approaches, whether heuristic or meta-heuristic, usually demands extensive manual intervention and has difficulty generalizing across diverse problem domains. The combination of Large Language Models (LLMs) and…
In many applications, model ensembling proves to be better than a single predictive model. Hence, it is the most common post-processing technique in Automated Machine Learning (AutoML). The most popular frameworks use ensembles at the…
Evolutionary algorithms (EAs) have achieved remarkable success in tackling complex combinatorial optimization problems. However, EAs often demand carefully-designed operators with the aid of domain expertise to achieve satisfactory…