LoRTA: Low Rank Tensor Adaptation of Large Language Models

Low Rank Adaptation (LoRA) is a popular Parameter Efficient Fine Tuning (PEFT) method that effectively adapts large pre-trained models for downstream tasks. LoRA parameterizes model updates using low-rank matrices at each layer, significantly reducing the number of trainable parameters and, consequently, resource requirements during fine-tuning. However, the lower bound on the number of trainable parameters remains high due to the use of the low-rank matrix model. In this paper, we address this limitation by proposing a novel approach that employs a low rank tensor parametrization for model updates. The proposed low rank tensor model can significantly reduce the number of trainable parameters, while also allowing for finer-grained control over adapter size. Our experiments on Natural Language Understanding, Instruction Tuning, Preference Optimization and Protein Folding benchmarks demonstrate that our method is both efficient and effective for fine-tuning large language models, achieving a substantial reduction in the number of parameters while maintaining comparable performance.

Space-Time Graph Neural Networks with Stochastic Graph Perturbations

Space-time graph neural networks (ST-GNNs) are recently developed architectures that learn efficient graph representations of time-varying data. ST-GNNs are particularly useful in multi-agent systems, due to their stability properties and their ability to respect communication delays between the agents. In this paper we revisit the stability properties of ST-GNNs and prove that they are stable to stochastic graph perturbations. Our analysis suggests that ST-GNNs are suitable for transfer learning on time-varying graphs and enables the design of generalized convolutional architectures that jointly process time-varying graphs and time-varying signals. Numerical experiments on decentralized control systems validate our theoretical results and showcase the benefits of traditional and generalized ST-GNN architectures.

Deep Convolutional Neural Networks for Multi-Target Tracking: A Transfer Learning Approach

Multi-target tracking (MTT) is a traditional signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements. In this paper, we revisit MTT from a deep learning perspective and propose convolutional neural network (CNN) architectures to tackle it. We represent the target states and sensor measurements as images. Thereby we recast the problem as a image-to-image prediction task for which we train a fully convolutional model. This architecture is motivated by a novel theoretical bound on the transferability error of CNN. The proposed CNN architecture outperforms a GM-PHD filter on the MTT task with 10 targets. The CNN performance transfers without re-training to a larger MTT task with 250 targets with only a $13\%$ increase in average OSPA.