Related papers: Non-Interfering Weight Fields: Treating Model Para…

How do we transfer the relevant knowledge from ever larger foundation models into small, task-specific downstream models that can run at much lower costs? Standard transfer learning using pre-trained weights as the initialization transfers…

Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. However, since current works tend to assume exclusivity or…

Large Transformer models have achieved impressive performance in many natural language tasks. In particular, Transformer based language models have been shown to have great capabilities in encoding factual knowledge in their vast amount of…

Large pre-trained models, or foundation models, have shown impressive performance when adapted to a variety of downstream tasks, often out-performing specialized models. Hypernetworks, neural networks that generate some or all of the…

Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks. Despite recent remarkable progress in state-of-the-art deep learning, deep…

Domain classification is the fundamental task in natural language understanding (NLU), which often requires fast accommodation to new emerging domains. This constraint makes it impossible to retrain all previous domains, even if they are…

Conventional deep learning models have limited capacity in learning multiple tasks sequentially. The issue of forgetting the previously learned tasks in continual learning is known as catastrophic forgetting or interference. When the input…

Generative models have recently been explored for synthesizing neural network weights. These approaches take neural network checkpoints as training data and aim to generate high-performing weights during inference. In this work, we examine…

One notable weakness of current machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning paradigm has emerged as a protocol to systematically…

Pre-trained models have achieved excellent performance on the dialogue task. However, for the continual increase of online chit-chat scenarios, directly fine-tuning these models for each of the new tasks not only explodes the capacity of…

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…

Recently, data-driven based Automatic Speech Recognition (ASR) systems have achieved state-of-the-art results. And transfer learning is often used when those existing systems are adapted to the target domain, e.g., fine-tuning, retraining.…

Catastrophic forgetting is the primary challenge that hinders continual learning, which refers to a neural network ability to sequentially learn multiple tasks while retaining previously acquired knowledge. Elastic Weight Consolidation, a…

We propose several ways of reusing subword embeddings and other weights in subword-aware neural language models. The proposed techniques do not benefit a competitive character-aware model, but some of them improve the performance of…

Learning user representations is a vital technique toward effective user modeling and personalized recommender systems. Existing approaches often derive an individual set of model parameters for each task by training on separate data.…

Machine unlearning (MU), which seeks to erase the influence of specific unwanted data from already-trained models, is becoming increasingly vital in model editing, particularly to comply with evolving data regulations like the ``right to be…

To address the issue of catastrophic forgetting in neural networks, we propose a novel, simple, and effective solution called neuron-level plasticity control (NPC). While learning a new task, the proposed method preserves the knowledge for…

Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…

Human being and different species of animals having the skills to gather, transferring knowledge, processing, fine-tune and generating information throughout their lifetime. The ability of learning throughout their lifespan is referred as…

While a diverse collection of continual learning (CL) methods has been proposed to prevent catastrophic forgetting, a thorough investigation of their effectiveness for processing sequential data with recurrent neural networks (RNNs) is…