The formulation is very similar to the method for learning positional node embeddings. Asynthetic molecular graph regression dataset, where thepredictedscore isgivenby the subtraction of computationally estimated propertieslogP SA. Thetask is to classify the nodes into 2 communities, testing the GNNs ability to recognize predetermined subgraphs. For the training parameters, we employed an Adam optimizer with alearning rate decay strategy initializedin{10 3,10 4}asper[15],withsomeminormodifications: ZINC[15]. We selected aninitial learning rateof7 10 4 and increased thepatiencefrom 10 to 25 to ensure convergence.

Recent developments in Parameter-Efficient Fine-Tuning (PEFT) methods for pre-trained deep neural networks have captured widespread interest.

Message Passing Graph Neural Networks (MPGNNs) have emerged as the preferred method for modeling complex interactions across diverse graph entities.

Large-scale foundation models are often adapted for specific downstream tasks after pre-training.

Fine-tuning large foundation models is essential for building expert models tailored to specialized tasks and domains, but fully updating billions of parameters is computationally prohibitive. Reducing the number of trainable parameters using parameter-efficient fine-tuning is therefore crucial not only to reduce training costs but also to mitigate storage, caching, and serving overheads during deployment. Prior works, such as Singular Vectors-guided Fine-Tuning, have shown that exploiting the geometry of pre-trained weights can significantly improve parameter-efficiency, but they lack a solid theoretical foundation. In this paper, we introduce Parameter-efficient Fine-tuning with Column Space Projection (PiCa), a novel theoretically grounded PEFT method. We prove that projecting gradients onto the principal column space of pre-trained weights provides an effective inductive bias for adaptation and further enhance parameter efficiency through a novel weight-sharing strategy. Across diverse NLP and vision tasks, PiCa consistently outperforms state-of-the-art baselines under comparable or smaller parameter budgets, demonstrating both theoretical rigor and practical effectiveness.

However, most existing approaches rely on global low-rank structures, which can overlook spatial patterns spread across the parameter space. In this work, we propose Localized LoRA, a generalized framework that models weight updates as a composition of low-rank matrices applied to structured blocks of the weight matrix. This formulation enables dense, localized updates throughout the parameter space--without increasing the total number of trainable parameters. We provide a formal comparison between global, diagonal-local, and fully localized low-rank approximations, and show that our method consistently achieves lower approximation error under matched parameter budgets. Experiments on both synthetic and practical settings demonstrate that Localized LoRA offers a more expressive and adaptable alternative to existing methods, enabling efficient fine-tuning with improved performance.

Large language models (LLMs) have not yet effectively leveraged the vast amounts of edge-device data, and federated learning (FL) offers a promising paradigm to collaboratively fine-tune LLMs without transferring private edge data to the cloud. To operate within the computation and communication constraints of edge devices, recent literature on federated fine-tuning of LLMs proposes the use of low-rank adaptation (LoRA) and similar parameter-efficient methods. However, LoRA-based methods suffer from accuracy degradation in FL settings, primarily because of data and computational heterogeneity across clients. We propose \textsc{Ravan}, an adaptive multi-head LoRA method that balances parameter efficiency and model expressivity by reparameterizing the weight updates as the sum of multiple LoRA heads $s_i\textbf{B}_i\textbf{H}_i\textbf{A}_i$ in which only the core matrices $\textbf{H}_i$ and their lightweight scaling factors $s_i$ are trained. These trainable scaling factors let the optimization focus on the most useful heads, recovering a higher-rank approximation of the full update without increasing the number of communicated parameters since clients upload $s_i\textbf{H}_i$ directly. Experiments on vision and language benchmarks show that \textsc{Ravan} improves test accuracy by 2-8\% over prior parameter-efficient baselines, making it a robust and scalable solution for federated fine-tuning of LLMs.