Related papers: Optimize Incompatible Parameters through Compatibi…
Integrating domain knowledge into neural networks is a central challenge in scientific machine learning. Three paradigms have emerged -- data-driven (Neural Ordinary Differential Equations, NODEs), soft-constrained (Physics-Informed Neural…
Deep nonlinear models pose a challenge for fitting parameters due to lack of knowledge of the hidden layer and the potentially non-affine relation of the initial and observed layers. In the present work we investigate the use of information…
Knowledge Tracing (KT) aims to model a student's learning state over time and predict their future performance. However, traditional KT methods often face challenges in explainability, scalability, and effective modeling of complex…
Deep Generative Models (DGMs) are versatile tools for learning data representations while adequately incorporating domain knowledge such as the specification of conditional probability distributions. Recently proposed DGMs tackle the…
Predicting diseases solely from patient-side information, such as demographics and self-reported symptoms, has attracted significant research attention due to its potential to enhance patient awareness, facilitate early healthcare…
Social recommendation task aims to predict users' preferences over items with the incorporation of social connections among users, so as to alleviate the sparse issue of collaborative filtering. While many recent efforts show the…
Explainability and effectiveness are two key aspects for building recommender systems. Prior efforts mostly focus on incorporating side information to achieve better recommendation performance. However, these methods have some weaknesses:…
Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…
An applied problem facing all areas of data science is harmonizing data sources. Joining data from multiple origins with unmapped and only partially overlapping features is a prerequisite to developing and testing robust, generalizable…
Knowledge Components (KCs) are foundational to adaptive learning systems, but their manual identification by domain experts is a significant bottleneck. While Large Language Models (LLMs) offer a promising avenue for automating this…
Knowledge tracing allows Intelligent Tutoring Systems to infer which topics or skills a student has mastered, thus adjusting curriculum accordingly. Deep Learning based models like Deep Knowledge Tracing (DKT) and Dynamic Key-Value Memory…
Cognitive diagnosis is a crucial task in computational education, aimed at evaluating students' proficiency levels across various knowledge concepts through exercises. Current models, however, primarily rely on students' answered exercises,…
Deep learning based data-driven approaches have been successfully applied in various image understanding applications ranging from object recognition, semantic segmentation to visual question answering. However, the lack of knowledge…
In artificial intelligence (AI), knowledge is the information required by an intelligent system to accomplish tasks. While traditional knowledge bases use discrete, symbolic representations, detecting knowledge encoded in the continuous…
Biological data are extremely diverse, complex but also quite sparse. The recent developments in deep learning methods are offering new possibilities for the analysis of complex data. However, it is easy to be get a deep learning model that…
Modular and composable transfer learning is an emerging direction in the field of Parameter Efficient Fine-Tuning, as it enables neural networks to better organize various aspects of knowledge, leading to improved cross-task generalization.…
Recent advances in deep learning have led to a surge of open-source models across diverse domains. While model merging offers a promising way to combine their strengths, existing approaches often suffer from parameter conflicts that degrade…
A composable infrastructure is defined as resources, such as compute, storage, accelerators and networking, that are shared in a pool and that can be grouped in various configurations to meet application requirements. This freedom to 'mix…
Deep learning has become increasingly popular in both supervised and unsupervised machine learning thanks to its outstanding empirical performance. However, because of their intrinsic complexity, most deep learning methods are largely…
Relying on either deep models or physical models are two mainstream approaches for solving inverse sample reconstruction problems in programmable illumination computational microscopy. Solutions based on physical models possess strong…