Related papers: Personalized Forgetting Mechanism with Concept-Dri…

One of the main motivations of studying continual learning is that the problem setting allows a model to accrue knowledge from past tasks to learn new tasks more efficiently. However, recent studies suggest that the key metric that…

Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as…

Deep Learning models have achieved remarkable performance in tasks such as image classification or generation, often surpassing human accuracy. However, they can struggle to learn new tasks and update their knowledge without access to…

We focus on the problem of Personalized Federated Continual Learning (PFCL): a group of distributed clients, each with a sequence of local tasks on arbitrary data distributions, collaborate through a central server to train a personalized…

Personalized recommendation is a key feature of intelligent tutoring systems, typically relying on accurate models of student knowledge. Knowledge Tracing (KT) models enable this by estimating a student's mastery based on their historical…

Machine unlearning seeks to remove the influence of particular data or class from trained models to meet privacy, legal, or ethical requirements. Existing unlearning methods tend to forget shallowly: phenomenon of an unlearned model pretend…

Knowledge Graph Embeddings (KGEs) support a wide range of downstream tasks over Knowledge Graphs (KGs). In practice, KGs evolve as new entities and facts are added, motivating Continual Knowledge Graph Embedding (CKGE) methods that update…

While federated learning is promising for privacy-preserving collaborative learning without revealing local data, it remains vulnerable to white-box attacks and struggles to adapt to heterogeneous clients. Federated distillation (FD), built…

Knowledge Tracing (KT) predicts future performance by modeling students' historical interactions, and understanding students' affective states can enhance the effectiveness of KT, thereby improving the quality of education. Although…

Despite deep neural networks have demonstrated extraordinary power in various applications, their superior performances are at expense of high storage and computational costs. Consequently, the acceleration and compression of neural…

Knowledge tracing (KT) is a field of study that predicts the future performance of students based on prior performance datasets collected from educational applications such as intelligent tutoring systems, learning management systems, and…

Personalized adaptive learning (PAL) stands out by closely monitoring individual students' progress and tailoring their learning paths to their unique knowledge and needs. A crucial technique for effective PAL implementation is knowledge…

Personalized Federated Continual Learning (PFCL) is a new practical scenario that poses greater challenges in sharing and personalizing knowledge. PFCL not only relies on knowledge fusion for server aggregation at the global…

Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue…

As privacy and security take center stage in AI, machine unlearning, the ability to erase specific knowledge from models, has garnered increasing attention. However, existing methods overly prioritize efficiency and aggressive forgetting,…

Continual learning addresses the problem of continuously acquiring and transferring knowledge without catastrophic forgetting of old concepts. While humans achieve continual learning via diverse neurocognitive mechanisms, there is a…

Continual learning-the ability to learn many tasks in sequence-is critical for artificial learning systems. Yet standard training methods for deep networks often suffer from catastrophic forgetting, where learning new tasks erases knowledge…

Accurate modeling of student knowledge is essential for large-scale online learning systems that are increasingly used for student training. Knowledge tracing aims to model student knowledge state given the student's sequence of learning…

Knowledge tracing (KT) enhances student learning by leveraging past performance to predict future performance. Current research utilizes models based on attention mechanisms and recurrent neural network structures to capture long-term…

Continual Test-Time Adaptation (CTTA) aims to quickly fine-tune the model during the test phase so that it can adapt to multiple unknown downstream domain distributions without pre-acquiring downstream domain data. To this end, existing…