Related papers: Grow, Don't Overwrite: Fine-tuning Without Forgett…

Neural networks can achieve excellent results in a wide variety of applications. However, when they attempt to sequentially learn, they tend to learn the new task while catastrophically forgetting previous ones. We propose a model that…

Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…

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…

In continual learning (CL), model growth enhances adaptability to new data. However, when model growth is applied improperly, especially in task-agnostic CL, where the entire grown model is used for inference, it can lead to severe…

The impressive performance of deep learning architectures is associated with a massive increase in model complexity. Millions of parameters need to be tuned, with training and inference time scaling accordingly, together with energy…

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

Machine learning systems perform well on pattern matching tasks, but their ability to perform algorithmic or logical reasoning is not well understood. One important reasoning capability is algorithmic extrapolation, in which models trained…

Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models tend to forget knowledge acquired during pretraining. In vision…

In this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encoder-decoder model for the open-domain dialogue response…

Continual fine-tuning aims to adapt a pre-trained backbone to new tasks sequentially while preserving performance on earlier tasks whose data are no longer available. Existing approaches fall into two categories which include input- and…

Large Language Models (LLMs) require instruction fine-tuning to perform different downstream tasks. However, the instruction fine-tuning phase still demands significant computational resources and labeled data, lacking a paradigm that can…

Real-world model deployments demand strong performance on narrow domains where data is often scarce. Typically, practitioners finetune models to specialize them, but this risks overfitting to the domain and forgetting general knowledge. We…

Recently the emergence of novel presentation attacks has drawn increasing attention to face anti-spoofing. However, existing methods tend to memorize data patterns from the training set, resulting in poor generalization to unknown attack…

Model brittleness is a key concern when deploying deep learning models in real-world medical settings. A model that has high performance at one institution may suffer a significant decline in performance when tested at other institutions.…

Our research demonstrates the significant benefits of using fine-tuning with explanations to enhance the performance of language models. Unlike prompting, which maintains the model's parameters, fine-tuning allows the model to learn and…

In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training.…

Adapting deep learning models to new domains often requires computationally intensive retraining and risks catastrophic forgetting. While fine-tuning enables domain-specific adaptation, it can reduce robustness to distribution shifts,…

The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a…

Feature transformation aims to extract a good representation (feature) space by mathematically transforming existing features. It is crucial to address the curse of dimensionality, enhance model generalization, overcome data sparsity, and…

In general class-incremental learning, researchers typically use sample sets as a tool to avoid catastrophic forgetting during continuous learning. At the same time, researchers have also noted the differences between class-incremental…