Related papers: Recommending Metamodel Concepts during Modeling Ac…
In deep learning, performance is strongly affected by the choice of architecture and hyperparameters. While there has been extensive work on automatic hyperparameter optimization for simple spaces, complex spaces such as the space of deep…
Domain Specific Languages are used to provide a tailored modelling notation for a specific application domain. There are currently two main approaches to DSLs: standard notations that are tailored by adding simple properties; new notations…
Ensembles are popular methods for solving practical supervised learning problems. They reduce the risk of having underperforming models in production-grade software. Although critical, methods for learning heterogeneous regression ensembles…
Meta-learning, also known as ``learning to learn'', enables models to acquire great generalization abilities by learning from various tasks. Recent advancements have made these models applicable across various fields without data…
With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dataset. In this paper, we propose a methodology that jointly…
Best-performing speech models are trained on large amounts of data in the language they are meant to work for. However, most languages have sparse data, making training models challenging. This shortage of data is even more prevalent in…
Deep learning fostered a leap ahead in automated skin lesion analysis in the last two years. Those models are expensive to train and difficult to parameterize. Objective: We investigate methodological issues for designing and evaluating…
Although deep models achieve high predictive performance, it is difficult for humans to understand the predictions they made. Explainability is important for real-world applications to justify their reliability. Many example-based…
Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…
Metamodeling refers to scenarios in ontologies in which classes and roles can be members of classes or occur in roles. This is a desirable modelling feature in several applications, but allowing it without restrictions is problematic for…
Automated machine learning (AutoML) has democratized the design of machine learning based systems, by automating model selection, hyperparameter tuning and feature engineering. However, the high computational cost associated with…
The use of conceptual models to foster requirements engineering has been proposed and evaluated as beneficial for several decades. For instance, goal-oriented requirements engineering or the specification of scenarios are commonly done…
We present a model-based testing approach to support automated test generation with domain-specific concepts. This includes a language expert who is an expert at building test models and domain experts who are experts in the domain of the…
Since the Transformer architecture emerged, language model development has grown, driven by their promising potential. Releasing these models into production requires properly understanding their behavior, particularly in sensitive domains…
Accurate understanding of users in terms of predicative segments play an essential role in the day to day operation of modern internet enterprises. Nevertheless, there are significant challenges that limit the quality of data, especially on…
The emergence of pre-trained models has significantly impacted Natural Language Processing (NLP) and Computer Vision to relational datasets. Traditionally, these models are assessed through fine-tuned downstream tasks. However, this raises…
Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when…
We propose a novel task-agnostic in-domain pre-training method that sits between generic pre-training and fine-tuning. Our approach selectively masks in-domain keywords, i.e., words that provide a compact representation of the target…
Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems have been solved in tasks such as game playing and robotics. Unfortunately, the sample complexity of most…
The growing number of pretrained models in Machine Learning (ML) presents significant challenges for practitioners. Given a new dataset, they need to determine the most suitable deep learning (DL) pipeline, consisting of the pretrained…