GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning

• URL: http://arxiv.org/abs/2512.06678v1
• Date: Sun, 07 Dec 2025 06:35:04 GMT
• Title: GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning
• Authors: Shrihari Sridharan, Deepak Ravikumar, Anand Raghunathan, Kaushik Roy,
• Abstract summary: GradientSpace is a framework that clusters samples directly in full-dimensional gradient space.<n>We introduce an online SVD-based algorithm that operates on LoRA gradients to identify latent skills without the infeasible cost of storing all sample gradients.<n>We show that routing to a single, appropriate expert outperforms expert ensembles used in prior work, while significantly reducing inference latency.
• Score: 13.559381851907778
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Instruction tuning is one of the key steps required for adapting large language models (LLMs) to a broad spectrum of downstream applications. However, this procedure is difficult because real-world datasets are rarely homogeneous; they consist of a mixture of diverse information, causing gradient interference, where conflicting gradients pull the model in opposing directions, degrading performance. A common strategy to mitigate this issue is to group data based on semantic or embedding similarity. However, this fails to capture how data influences model parameters during learning. While recent works have attempted to cluster gradients directly, they randomly project gradients into lower dimensions to manage memory, which leads to accuracy loss. Moreover, these methods rely on expert ensembles which necessitates multiple inference passes and expensive on-the-fly gradient computations during inference. To address these limitations, we propose GradientSpace, a framework that clusters samples directly in full-dimensional gradient space. We introduce an online SVD-based algorithm that operates on LoRA gradients to identify latent skills without the infeasible cost of storing all sample gradients. Each cluster is used to train a specialized LoRA expert along with a lightweight router trained to select the best expert during inference. We show that routing to a single, appropriate expert outperforms expert ensembles used in prior work, while significantly reducing inference latency. Our experiments across mathematical reasoning, code generation, finance, and creative writing tasks demonstrate that GradientSpace leads to coherent expert specialization and consistent accuracy gains over state-of-the-art clustering methods and finetuning techniques.

Related papers

• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Linearly Convergent Mixup Learning [0.0]
  We present two novel algorithms that extend to a broader range of binary classification models.<n>Unlike gradient-based approaches, our algorithms do not require hyper parameters like learning rates, simplifying their implementation and optimization.<n>Our algorithms achieve faster convergence to the optimal solution compared to descent gradient approaches, and that mixup data augmentation consistently improves the predictive performance across various loss functions.
  arXiv  Detail & Related papers  (2025-01-14T02:33:40Z)
• FLOPS: Forward Learning with OPtimal Sampling [1.694989793927645]
  gradient-based computation methods have recently gained focus for learning with only forward passes, also referred to as queries.<n> Conventional forward learning consumes enormous queries on each data point for accurate gradient estimation through Monte Carlo sampling.<n>We propose to allocate the optimal number of queries over each data in one batch during training to achieve a good balance between estimation accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2024-10-08T12:16:12Z)
• Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models [56.00251589760559]
  Large language models (LLMs) can act as gradient priors in a zero-shot setting.<n>We introduce LM-GC, a novel method that integrates LLMs with arithmetic coding.<n>Experiments indicate that LM-GC surpasses existing state-of-the-art lossless compression methods.
  arXiv  Detail & Related papers  (2024-09-26T13:38:33Z)
• A Historical Trajectory Assisted Optimization Method for Zeroth-Order Federated Learning [24.111048817721592]
  Federated learning heavily relies on distributed gradient descent techniques. In the situation where gradient information is not available, gradients need to be estimated from zeroth-order information. We propose a non-isotropic sampling method to improve the gradient estimation procedure.
  arXiv  Detail & Related papers  (2024-09-24T10:36:40Z)
• GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization [52.55628139825667]
  Federated Learning (FL) has emerged as a promising distributed machine learning framework to preserve clients' privacy. Recent studies find that an attacker can invert the shared gradients and recover sensitive data against an FL system by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD), which disassembles the GAN model and searches the feature domains of the intermediate layers.
  arXiv  Detail & Related papers  (2023-08-09T04:34:21Z)
• Unsupervised Anomaly Detection via Nonlinear Manifold Learning [0.0]
  Anomalies are samples that significantly deviate from the rest of the data and their detection plays a major role in building machine learning models. We introduce a robust, efficient, and interpretable methodology based on nonlinear manifold learning to detect anomalies in unsupervised settings.
  arXiv  Detail & Related papers  (2023-06-15T18:48:10Z)
• Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning [112.69497636932955]
  Federated learning aims to train models across different clients without the sharing of data for privacy considerations. We study how data heterogeneity affects the representations of the globally aggregated models. We propose sc FedDecorr, a novel method that can effectively mitigate dimensional collapse in federated learning.
  arXiv  Detail & Related papers  (2022-10-01T09:04:17Z)
• The Manifold Hypothesis for Gradient-Based Explanations [55.01671263121624]
  gradient-based explanation algorithms provide perceptually-aligned explanations. We show that the more a feature attribution is aligned with the tangent space of the data, the more perceptually-aligned it tends to be. We suggest that explanation algorithms should actively strive to align their explanations with the data manifold.
  arXiv  Detail & Related papers  (2022-06-15T08:49:24Z)
• Style Curriculum Learning for Robust Medical Image Segmentation [62.02435329931057]
  Deep segmentation models often degrade due to distribution shifts in image intensities between the training and test data sets. We propose a novel framework to ensure robust segmentation in the presence of such distribution shifts.
  arXiv  Detail & Related papers  (2021-08-01T08:56:24Z)
• Variational Auto Encoder Gradient Clustering [0.0]
  Clustering using deep neural network models have been extensively studied in recent years. This article investigates how probability function gradient ascent can be used to process data in order to achieve better clustering. We propose a simple yet effective method for investigating suitable number of clusters for data, based on the DBSCAN clustering algorithm.
  arXiv  Detail & Related papers  (2021-05-11T08:00:36Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach [11.986523531539165]
  Federated learning (FL) is an emerging technique for training machine learning models using geographically dispersed data. gradient sparsification (GS) can be applied, where instead of the full gradient, only a small subset of important elements of the gradient is communicated. We propose a novel online learning formulation and algorithm for automatically determining the near-optimal communication and trade-off.
  arXiv  Detail & Related papers  (2020-01-14T13:09:23Z)

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.