UniRank: Unified Rank Allocation for Low-Rank LLM Compression

• URL: http://arxiv.org/abs/2606.21847v1
• Date: Sat, 20 Jun 2026 03:10:33 GMT
• Title: UniRank: Unified Rank Allocation for Low-Rank LLM Compression
• Abstract summary: We formulate global low-rank allocation as a sorting-and-truncation pipeline.<n>We verify the strong correlation between high input-output cosine similarity and low effective rank.<n>We propose rank-preserving fine-tuning, which performs direct LoRA tuning on decomposed weights.
• Score: 9.742379971053806
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Low-rank decomposition serves as a promising compression paradigm for large language models, however, rank allocation remains challenging: manual rules lack generalizability, and learning-based approaches incur heavy computational overhead. To address these issues, we formulate global low-rank allocation as a sorting-and-truncation pipeline, and score each singular component via dual criteria: \textbf{Local} singular energy ratio that quantifies the intrinsic importance within the decomposed parameter matrix and \textbf{Global} functional importance (measured by input-output cosine similarity) that evaluates the functional significance of decomposed modules. We verify the strong correlation between high input-output cosine similarity and low effective rank through geometric interpretation and experimental validation. Furthermore, we propose rank-preserving fine-tuning, which performs direct LoRA tuning on decomposed weights and avoids extra information loss caused by re-truncation in conventional merging pipelines. Empirical results confirm that our method delivers sustained performance enhancements when combined with models featuring distinct decomposition schemes, model sizes and architectural designs, e.g. in one-shot compression without further fine-tuning, our method reduces perplexity by up to 50\% compared with uniform and heuristic allocation baselines. Code will be available at https://github.com/EIT-NLP/LLM-Pruning.

Related papers

• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution [5.770893169582546]
  This work reframes attribution as subset-level counterfactual utility prediction.<n>We introduce GRASP, an interaction-aware surrogate.<n>It decisively outperforms existing scalable baselines.
  arXiv  Detail & Related papers  (2026-06-05T04:17:50Z)
• ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression [5.223477157195793]
  "lost in the middle" phenomenon degrades ranking quality as input length grows.<n>Inference latency scales super-linearly with sequence length, rendering listwise reranking impractical for industrial deployment.<n>We present ResRank, a unified retrieval-reranking framework that fundamentally addresses both challenges.
  arXiv  Detail & Related papers  (2026-04-24T03:11:51Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• Simple yet Effective: Low-Rank Spatial Attention for Neural Operators [12.794762297826848]
  We introduce Low-Rank Spatial Attention (LRSA) as a clean and direct instantiation of this template.<n>Unlike prior approaches that often rely on non-standard aggregation or normalization modules, LRSA is built purely from standard Transformer primitives.<n>In our experiments, such a simple construction is sufficient to achieve high accuracy, yielding an average error reduction of over 17%.
  arXiv  Detail & Related papers  (2026-04-04T04:15:01Z)
• Robust low-rank estimation with multiple binary responses using pairwise AUC loss [0.0]
  Multiple binary responses arise in many modern data-analytic problems.<n>Low-rank models offer a natural way to encode latent dependence across tasks.<n>Existing methods for binary data are largely likelihood-based and focus on pointwise classification.
  arXiv  Detail & Related papers  (2026-01-13T15:00:10Z)
• NDCG-Consistent Softmax Approximation with Accelerated Convergence [67.10365329542365]
  We propose novel loss formulations that align directly with ranking metrics.<n>We integrate the proposed RG losses with the highly efficient Alternating Least Squares (ALS) optimization method.<n> Empirical evaluations on real-world datasets demonstrate that our approach achieves comparable or superior ranking performance.
  arXiv  Detail & Related papers  (2025-06-11T06:59:17Z)
• Optimizing Singular Spectrum for Large Language Model Compression [95.7621116637755]
  We introduce SoCo, a novel compression framework that learns to rescale the decomposed components of SVD in a data-driven manner.<n>Thanks to the learnable singular spectrum, SoCo adaptively prunes components according to the sparsified importance scores.<n> Experimental evaluations across multiple LLMs and benchmarks demonstrate that SoCo surpasses the state-of-the-art methods in model compression.
  arXiv  Detail & Related papers  (2025-02-20T23:18:39Z)
• Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models [1.6385815610837167]
  Pivoting Factorization (PIFA) is a novel low-rank representation that unsupervisedly learns a compact form of any low-rank representation.<n>PIFA achieves 24.2% additional memory savings and 24.6% faster inference over low-rank layers at rank = 50% of dimension.<n>MPIFA, combining M and PIFA into an end-to-end framework, significantly outperforms existing low-rank pruning methods.
  arXiv  Detail & Related papers  (2025-01-31T12:36:31Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation [77.7420231319632]
  We adapt contextual generation of categorical sequences to a policy gradient estimator, which evaluates a set of correlated Monte Carlo (MC) rollouts for variance control. We also demonstrate the use of correlated MC rollouts for binary-tree softmax models, which reduce the high generation cost in large vocabulary scenarios.
  arXiv  Detail & Related papers  (2019-12-31T03:01:55Z)

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.