Related papers: Parameter-efficient Multi-task Fine-tuning for Tra…
Hard parameter sharing in multi-domain learning (MDL) allows domains to share some of the model parameters to reduce storage cost while improving prediction accuracy. One common sharing practice is to share the bottom layers of a deep…
Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is available in different task-language combinations. To exploit such…
Graph foundation models have demonstrated remarkable adaptability across diverse downstream tasks through large-scale pretraining on graphs. However, existing implementations of the backbone model, graph transformers, are typically limited…
Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be rapidly adapted on the fly for specific downstream tasks, without requiring additional fine-tuning.…
Multi-task learning (MTL) has been successfully used in many real-world applications, which aims to simultaneously solve multiple tasks with a single model. The general idea of multi-task learning is designing kinds of global parameter…
In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…
Foundation models have achieved great advances in multi-task learning with a unified interface of unimodal and multimodal tasks. However, the potential of such multi-task learners has not been exploited during transfer learning. In this…
Link Prediction (LP) is a critical task in graph machine learning. While Graph Neural Networks (GNNs) have significantly advanced LP performance recently, existing methods face key challenges including limited supervision from sparse…
Large language models (LLMs) have achieved remarkable success in various tasks, such as decision-making, reasoning, and question answering. They have been widely used in edge devices. However, fine-tuning LLMs to specific tasks at the edge…
Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may…
Compact neural network offers many benefits for real-world applications. However, it is usually challenging to train the compact neural networks with small parameter sizes and low computational costs to achieve the same or better model…
Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…
Parameter-efficient fine-tuning (PEFT) techniques, such as adapter tuning, aim to fine-tune a pre-trained language model (PLM) using a minimal number of parameters for a specific task or profile. Although adapter tuning provides increased…
Accurate hardware performance models are critical to efficient code generation. They can be used by compilers to make heuristic decisions, by superoptimizers as a minimization objective, or by autotuners to find an optimal configuration for…
Adapters, a plug-in neural network module with some tunable parameters, have emerged as a parameter-efficient transfer learning technique for adapting pre-trained models to downstream tasks, especially for natural language processing (NLP)…
Federated learning enables many applications benefiting distributed and private datasets of a large number of potential data-holding clients. However, different clients usually have their own particular objectives in terms of the tasks to…
Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…
Fine-tuning is a popular method for adapting text-to-speech (TTS) models to new speakers. However this approach has some challenges. Usually fine-tuning requires several hours of high quality speech per speaker. There is also that…
In this paper we present an alternative strategy for fine-tuning the parameters of a network. We named the technique Gradual Tuning. Once trained on a first task, the network is fine-tuned on a second task by modifying a progressively…
Deep learning has shown substantial progress in image analysis. However, the computational demands of large, fully trained models remain a consideration. Transfer learning offers a strategy for adapting pre-trained models to new tasks.…