STAR: Spectral Truncation and Rescale for Model Merging

• URL: http://arxiv.org/abs/2502.10339v1
• Date: Fri, 14 Feb 2025 17:59:58 GMT
• Title: STAR: Spectral Truncation and Rescale for Model Merging
• Authors: Yu-Ang Lee, Ching-Yun Ko, Tejaswini Pedapati, I-Hsin Chung, Mi-Yen Yeh, Pin-Yu Chen,
• Abstract summary: A key challenge in model merging is the seemingly inevitable decrease in task performance as the number of models increases.<n>We propose $mathbfS$pectral $mathbfT$runcation $mathbfA$nd $mathbfR$escale (STAR) that aims at mitigating merging conflicts''<n>We demonstrate the effectiveness of STAR through extensive model merging cases on diverse NLP tasks.
• Score: 48.19545750399348
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model merging is an efficient way of obtaining a multi-task model from several pretrained models without further fine-tuning, and it has gained attention in various domains, including natural language processing (NLP). Despite the efficiency, a key challenge in model merging is the seemingly inevitable decrease in task performance as the number of models increases. In this paper, we propose $\mathbf{S}$pectral $\mathbf{T}$runcation $\mathbf{A}$nd $\mathbf{R}$escale (STAR) that aims at mitigating ``merging conflicts'' by truncating small components in the respective spectral spaces, which is followed by an automatic parameter rescaling scheme to retain the nuclear norm of the original matrix. STAR requires no additional inference on original training data and is robust to hyperparamater choice. We demonstrate the effectiveness of STAR through extensive model merging cases on diverse NLP tasks. Specifically, STAR works robustly across varying model sizes, and can outperform baselines by 4.2$\%$ when merging 12 models on Flan-T5. Our code is publicly available at https://github.com/IBM/STAR.

Related papers

• Intention-Conditioned Flow Occupancy Models [69.79049994662591]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging [38.12136955174922]
  Fine-tuning large language models (LMs) for individual tasks yields strong performance but is expensive for deployment and storage.<n>Recent works explore model merging to combine multiple task-specific models into a single multi-task model without additional training.<n>Existing merging methods often fail for models fine-tuned with low-rank adaptation (LoRA), due to significant performance degradation.
  arXiv  Detail & Related papers  (2025-05-28T23:28:12Z)
• NAN: A Training-Free Solution to Coefficient Estimation in Model Merging [61.36020737229637]
  We show that the optimal merging weights should scale with the amount of task-specific information encoded in each model.<n>We propose NAN, a simple yet effective method that estimates model merging coefficients via the inverse of parameter norm.<n>NAN is training-free, plug-and-play, and applicable to a wide range of merging strategies.
  arXiv  Detail & Related papers  (2025-05-22T02:46:08Z)
• If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs [48.95875673503714]
  We study merging "generalist" models trained on many tasks.<n>Our algorithm tunes the weight of each checkpoint in a linear combination, resulting in an optimal model.<n>Good merges tend to include almost all checkpoints with non-zero weights, indicating that even seemingly bad initial checkpoints can contribute to good final merges.
  arXiv  Detail & Related papers  (2024-12-05T13:12:51Z)
• Nudging: Inference-time Alignment of LLMs via Guided Decoding [18.530367090350605]
  Large language models (LLMs) require alignment to effectively and safely follow user instructions.<n>This process requires training an aligned version for every base model, resulting in significant computational overhead.<n>We propose NUDGING, a training-free algorithm that aligns any base model at inference time using a small aligned model.
  arXiv  Detail & Related papers  (2024-10-11T23:24:38Z)
• What Matters for Model Merging at Scale? [94.26607564817786]
  Model merging aims to combine multiple expert models into a more capable single model. Previous studies have primarily focused on merging a few small models. This study systematically evaluates the utility of model merging at scale.
  arXiv  Detail & Related papers  (2024-10-04T17:17:19Z)
• HM3: Heterogeneous Multi-Class Model Merging [0.0]
  We explore training-free model merging techniques to consolidate auxiliary guard-rail models into a single, multi-functional model. We propose Heterogeneous Multi-Class Model Merging (HM3) as a simple technique for merging multi-class classifiers with heterogeneous label spaces. We report promising results for merging BERT-based guard models, some of which attain an average F1-score higher than the source models while reducing the inference time by up to 44%.
  arXiv  Detail & Related papers  (2024-09-27T22:42:45Z)
• Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis [17.989809995141044]
  We propose CCA Merge, which is based on Corre Analysis Analysis. We show that CCA works significantly better than past methods when more than 2 models are merged.
  arXiv  Detail & Related papers  (2024-07-07T14:21:04Z)
• PLeaS -- Merging Models with Permutations and Least Squares [43.17620198572947]
  We propose a new two-step algorithm to merge models-termed PLeaS. PLeaS partially matches nodes in each layer by maximizing alignment. It computes the weights of the merged model as a layer-wise Least Squares solution.
  arXiv  Detail & Related papers  (2024-07-02T17:24:04Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)
• Training-Free Pretrained Model Merging [38.16269074353077]
  We propose an innovative model merging framework, coined as merging under dual-space constraints (MuDSC) In order to enhance usability, we have also incorporated adaptations for group structure, including Multi-Head Attention and Group Normalization.
  arXiv  Detail & Related papers  (2024-03-04T06:19:27Z)
• AdaMerging: Adaptive Model Merging for Multi-Task Learning [68.75885518081357]
  This paper introduces an innovative technique called Adaptive Model Merging (AdaMerging) It aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data. Compared to the current state-of-the-art task arithmetic merging scheme, AdaMerging showcases a remarkable 11% improvement in performance.
  arXiv  Detail & Related papers  (2023-10-04T04:26:33Z)
• Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity [67.02490430380415]
  We show that model-based MARL achieves a sample complexity of $tilde O(|S||B|(gamma)-3epsilon-2)$ for finding the Nash equilibrium (NE) value up to some $epsilon$ error. We also show that such a sample bound is minimax-optimal (up to logarithmic factors) if the algorithm is reward-agnostic, where the algorithm queries state transition samples without reward knowledge.
  arXiv  Detail & Related papers  (2020-07-15T03:25:24Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.