Related papers: Multi-concept Model Immunization through Different…
Globally operating enterprises selling large and complex products and services often have to deal with situations where variability models are locally developed to take into account the requirements of local markets. For example, cars sold…
Extracting medical knowledge from healthcare texts enhances downstream tasks like medical knowledge graph construction and clinical decision-making. However, the construction and application of knowledge extraction models lack automation,…
Personalized text-to-image diffusion models (e.g., DreamBooth, LoRA) enable users to synthesize high-fidelity avatars from a few reference photos for social expression. However, once these generations are shared on social media platforms…
Envelope model also known as multivariate regression model was proposed to solve the multiple response regression problems. It measures the linear association between predictors and multiple responses by using the minimal reducing subspace…
Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain. Hence, a crucial aspect is to properly combine different sources based on their relations. In this paper, we…
Controlling infectious diseases is a major health priority because they can spread and infect humans, thus evolving into epidemics or pandemics. Therefore, early detection of infectious diseases is a significant need, and many researchers…
Machine learning (ML) models are increasingly being used in application domains that often involve working together with human experts. In this context, it can be advantageous to defer certain instances to a single human expert when they…
This paper solves a generalized version of the problem of multi-source model adaptation for semantic segmentation. Model adaptation is proposed as a new domain adaptation problem which requires access to a pre-trained model instead of data…
The concept of personalised medicine in cancer therapy is becoming increasingly important. There already exist drugs administered specifically for patients with tumours presenting well-defined mutations. However, the field is still in its…
Closure problems are omnipresent when simulating multiscale systems, where some quantities and processes cannot be fully prescribed despite their effects on the simulation's accuracy. Recently, scientific machine learning approaches have…
Distributed representations of medical concepts have been used to support downstream clinical tasks recently. Electronic Health Records (EHR) capture different aspects of patients' hospital encounters and serve as a rich source for…
Concept-based models aim to explain model decisions with human-understandable concepts. However, most existing approaches treat concepts as numerical attributes, without providing complementary visual explanations that could localize the…
Recent advances in text-to-image diffusion models have enabled the photorealistic generation of images from text prompts. Despite the great progress, existing models still struggle to generate compositional multi-concept images naturally,…
Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…
Fueled by breakthrough technology developments, the biological, biomedical, and behavioral sciences are now collecting more data than ever before. There is a critical need for time- and cost-efficient strategies to analyze and interpret…
The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…
The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging interpretable-by-design methods, which aim to redesign ML algorithms for…
Effective utilization of Multiple-Instruction-Multiple-Data (MIMD) parallel computers requires the application of good load balancing techniques. In this paper we show that heuristics derived from observation of complex natural systems,…
Masking strategies commonly employed in natural language processing are still underexplored in vision tasks such as concept learning, where conventional methods typically rely on full images. However, using masked images diversifies…
Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like…