Related papers: Grow, Don't Overwrite: Fine-tuning Without Forgett…
In real-world applications, learning-enabled systems often undergo iterative model development to address challenging or emerging tasks, which involve collecting new data, training a new model and validating the model. This continual model…
Lifelong learning aims to develop machine learning systems that can learn new tasks while preserving the performance on previous learned tasks. In this paper we present a method to overcome catastrophic forgetting on convolutional neural…
Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This ability is limited in the current deep neural networks by a…
Deep neural networks have revolutionized numerous research fields and applications. Despite their widespread success, a fundamental limitation known as catastrophic forgetting remains, where models fail to retain their ability to perform…
A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the network's filters. Innovations in network architecture such as…
Catastrophic forgetting is a pervasive issue for pre-trained language models (PLMs) during continual learning, where models lose previously acquired knowledge when sequentially trained on a series of tasks. The model's ability to retain old…
This paper considers continual learning of large-scale pretrained neural machine translation model without accessing the previous training data or introducing model separation. We argue that the widely used regularization-based methods,…
When incrementally trained on new classes, deep neural networks are subject to catastrophic forgetting which leads to an extreme deterioration of their performance on the old classes while learning the new ones. Using a small memory…
Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data, however, this process might suffer from privacy issues and violations of data protection regulations. As a…
Matching animal-like flexibility in recognition and the ability to quickly incorporate new information remains difficult. Limits are yet to be adequately addressed in neural models and recognition algorithms. This work proposes a…
Large pre-trained language models (PLMs) have demonstrated strong performance on natural language understanding (NLU) tasks through fine-tuning. However, fine-tuned models still suffer from overconfident predictions, especially in…
This paper explores the possibility of extending the capability of pre-trained neural image compressors (e.g., adapting to new data or target bitrates) without breaking backward compatibility, the ability to decode bitstreams encoded by the…
Large language models (LLMs) excel in various tasks but are primarily trained on text data, limiting their application scope. Expanding LLM capabilities to include vision-language understanding is vital, yet training them on multimodal data…
Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to new languages, a barrier to making their capabilities…
Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…
Multitask learning assumes that models capable of learning from multiple tasks can achieve better quality and efficiency via knowledge transfer, a key feature of human learning. Though, state of the art ML models rely on high customization…
Federated fine-tuning (FedFT) of large language models (LLMs) has emerged as a promising solution for adapting models to distributed data environments while ensuring data privacy. Existing FedFT methods predominantly utilize…
Large language models store all learned knowledge in a single, fixed weight vector. Teaching a model new capabilities requires modifying those same weights, inevitably degrading previously acquired knowledge. This fundamental limitation,…
Currently used semantic parsing systems deployed in voice assistants can require weeks to train. Datasets for these models often receive small and frequent updates, data patches. Each patch requires training a new model. To reduce training…
Rehearsal is one of the key techniques for mitigating catastrophic forgetting and has been widely adopted in continual learning algorithms due to its simplicity and practicality. However, the theoretical understanding of how rehearsal scale…