TopoTuner is competitive with full fine-tuning while training only 1-2% of the model parameters, and outperforms LoRA in 7 out of 9 model-dataset settings, which can change up to 39.57% of the projection parameters.
Abstract
Full fine-tuning remains a strong way to adapt pretrained LLMs, but it updates all weights and can be expensive. LoRA reduces the number of trainable parameters, but it does not directly answer which pretrained components should be trained and which can be frozen during adaptation. We introduce TopoTuner, a topology-guided fine-tuning framework for selective freezing of attention projection matrices. \method treats each projection matrix as a row cloud and uses Wasserstein distances between persistence diagrams to measure how its topology changes during fine-tuning. TopoTuner learns a reusable freezing profile from a source dataset and transfers it to efficiently fine-tune models on out-of-domain datasets, evaluating whether task-specific topological drift generalizes across question answering and sentiment analysis tasks. Across LLaMA-3.1-8B, Mistral-7B-v0.3, and Qwen3-8B-Base, TopoTuner is competitive with full fine-tuning while training only 1-2\% of the model parameters, and outperforms LoRA in 7 out of 9 model-dataset settings, which can change up to 39.57\% of the projection parameters. Along with minimized updates, TopoTuner reduces training time by 20.4\% relative to full fine-tuning and 5.5\% relative to LoRA on average. TopoTuner opens a new direction for reusable freezing profiles, where fine-tuning behavior learned on one dataset can be shared across multiple tasks.
Large language models (LLMs) remain expensive to fine-tune because full-parameter updates require substantial memory, compute, and per-task storage. We study whether saliency signals originally developed for pruning can be reused to choose where a model should adapt. We propose Super, a sparse parameter-efficient fine-tuning (PEFT) method that fixes a small trainable support using a Wanda-style activation-weighted magnitude score [Sun et al., 2023] computed from a calibration pass. We then introduce Supra, a hybrid adapter that combines this sparse update with LoRA while preserving a matched trainable-parameter budget through a simple budget-splitting rule. In single-seed Math17K arithmetic experiments on Llama-3.2-1B and Meta-Llama-3-8B, the best Super/Supra variants achieve the highest average accuracy among the tested schedule-selected adapter configurations. We also include a PaFi-style magnitude-only support as a closest training-free sparse baseline and find that low-score supports under both magnitude and Wanda-style orderings can be effective. These results suggest that simple pruning-inspired orderings can provide useful fixed sparse supports for PEFT, especially when combined with low-rank adapters.
Ivan D. Ilin, Philip Zmushko, Peter Richtárik· 0 citations
Fine-tuning large language models (LLMs) is an effective approach to enhancing their performance on specialized downstream tasks. Among the various techniques, low-rank adaptation has garnered significant attention due to its ability to maintain the full performance of fine-tuning while enhancing computational efficiency. However, existing approaches often rely on manually specified and fixed hyperparameters to identify the trainable components within weight matrices, resulting in suboptimal performance and low parameter efficiency. This paper presents a novel Le arnable Lo w-R ank A daptation (LeLoRA) framework that utilizes dynamically learned fine-tuning strategies to facilitate the effective adaptation of LLMs. Our framework integrates an LLM with a policy network that automatically and adaptively generates matrix-specific adaptation strategies to identify the trainable components of each weight matrix, taking into account their unique characteristics, such as singular values and matrix norms. A reinforcement learning-based optimization algorithm is then employed to iteratively update the LLM and the policy network, ensuring that the generated strategies adapt in real time to the evolving states of the LLM. Extensive experiments have been conducted across various natural language processing tasks. The results across ten different LLMs, ranging from 125M to 70B parameters, provide compelling evidence that LeLoRA consistently outperforms existing baselines in adapting LLMs.
Xiaoling Zhou, Mingjie Zhang, Zhemg Lee et al.· Annual Meeting of the Associ...· 0 citations
The performance of deep learning models crucially depends on the settings of hyperparameters like learning rate, initialization scale, and weight decay. Hyperparameter transfer aims to make near-optimal hyperparameter settings consistent across model scale, so that large models can be optimized by proxy tuning their smaller, cheaper-to-optimize counterparts. While transfer principles are well-studied in the context of dense neural networks in language and vision tasks, they remain comparatively under-explored for graph neural networks (GNNs). We develop and validate a transfer parameterization for GNNs trained with SGD, Adam, and AdamW. Through theoretical scaling analyses and controlled experiments, we show that the proposed parameterization yields stable feature updates, learning rate transfer, and improved performance as width and depth increase. For SGD, we identify graph-dependent first-layer correction factors and show that their use can accelerate early training in graphs with sparse bag-of-words inputs. For Adam, we explore how different message passing normalizations affect early- and late-training transfer behavior, illustrating the importance of message passing normalization and advocating for an associated hyperparameter. For AdamW, we adapt a parameterization that allows for the joint transfer of weight decay and learning rate. Together, these results provide a practical recipe for scaling GNNs across a variety of learning tasks and training scenarios.
The rapid advancement of large language models (LLMs) has revolutionized natural language processing, yet their enormous parameter size presents significant challenges for fine-tuning on downstream tasks. While parameter-efficient fine-tuning (PEFT) methods such as Low-Rank Adaptation (LoRA) and Quantized LoRA (QLoRA) have substantially reduced computational requirements, they often introduce knowledge misalignment and representation degradation during adaptation. To bridge this gap, we propose GLA-LoRA, a novel PEFT framework centered on Global-Local Knowledge Alignment. Our approach establishes a unified learning strategy that synergistically integrates multi-granular contrastive learning with knowledge distillation. GLA-LoRA explicitly preserves dataset-wide semantic structures through global contrastive learning and maintains sample-level feature consistency via local invariance learning, while a teacher model guides the adaptation to retain the original model's knowledge. Extensive evaluations across eight benchmarks, spanning six GLUE tasks and two intent detection datasets, demonstrate that GLA-LoRA consistently outperforms strong baselines including standard LoRA and QLoRA. Under identical parameter budgets, GLA-LoRA achieves consistent and significant improvements over standard LoRA across three base models and eight benchmark datasets. On sentence-level classification and regression tasks, our method yields average accuracy gains of 1.4%, 1.1%, and 1.2% on LLaMA2-7B, RoBERTabase, and BERTLarge, respectively. For intent detection (CLINC and HWU), it achieves even more pronounced improvements, with up to 2.3% accuracy gain on BERTLarge. These results establish that explicit global-local knowledge alignment is essential for achieving high-fidelity, parameter-efficient fine-tuning across diverse language tasks.
Pruning is essential for the efficient deployment of Large Language Models (LLMs); however, it causes severe performance degradation due to the structural distortion induced by sparsity. Existing recovery strategies, such as LoRA, predominantly employ global fine-tuning, often overlooking the mechanistic root of this degradation: the layer-wise accumulation and amplification of local errors. To address this limitation, we propose LaCo ( La yer-wise Co mpensation), a framework that reori-ents the recovery paradigm from global adaptation to hierarchical representation alignment. By sequentially optimizing each layer to re-construct the model’s hidden states, LaCo effectively intercepts the error propagation chain at its source. Extensive experiments demonstrate that LaCo surpasses parameter-efficient baselines in both perplexity reduction and zero-shot reasoning. Notably, it reduces recovery-time memory usage to approximately 1 / 7 of the baseline and requires only 2,048 unlabeled samples to match a LoRA model trained on 50k examples—achieving a ∼ 25 × improvement in data efficiency.
Yingen Liu, Fan Wu, Xuyan Pan et al.· Annual Meeting of the Associ...· 0 citations
Large language model (LLM)-based rerankers have demonstrated strong performance in information retrieval tasks, but adapting them to specialized domains remains challenging due to the substantial cost and effort required to construct high-quality domain-specific training datasets. To address this limitation, we leverage task vectors derived from continuous pretraining as a mechanism for transferring domain knowledge. However, existing task vector integration methods are highly sensitive to scaling factors and can lead to unstable performance across domains and model scales. In this work, we propose a fine-grained task vector adaptation method that learns parameter-wise scaling coefficients for the task vector. These coefficients are optimized using a language modeling objective while keeping all model parameters fixed, enabling effective integration of domain-specific knowledge without degrading reranking capabilities. Experiments on a general-domain benchmark and five specialized domains across two model scales demonstrate that our method provides stable improvements across most domains and avoids the degradation observed with fixed task vector scaling.
Sanghyun Cho, Myeongjin Lee, Jong-hun Shin et al.· Annual International ACM SIG...· 0 citations