Sparsified State-Space Models are Efficient Highway Networks

• URL: http://arxiv.org/abs/2505.20698v1
• Date: Tue, 27 May 2025 04:07:23 GMT
• Title: Sparsified State-Space Models are Efficient Highway Networks
• Authors: Woomin Song, Jihoon Tack, Sangwoo Mo, Seunghyuk Oh, Jinwoo Shin,
• Abstract summary: State-space models (SSMs) offer an alternative to Transformers by replacing expensive self-attention with linear recurrences.<n>We propose a simple yet effective trick to enhance SSMs within given computational budgets by sparsifying them.<n>Simba is a hierarchical sparsification method for SSMs based on token pruning.
• Score: 52.29954079160793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-space models (SSMs) offer a promising architecture for sequence modeling, providing an alternative to Transformers by replacing expensive self-attention with linear recurrences. In this paper, we propose a simple yet effective trick to enhance SSMs within given computational budgets by sparsifying them. Our intuition is that tokens in SSMs are highly redundant due to gradual recurrent updates, and dense recurrence operations block the delivery of past information. In particular, we observe that upper layers of SSMs tend to be more redundant as they encode global information, while lower layers encode local information. Motivated by this, we introduce Simba, a hierarchical sparsification method for SSMs based on token pruning. Simba sparsifies upper layers more than lower layers, encouraging the upper layers to behave like highways. To achieve this, we propose a novel token pruning criterion for SSMs, measuring the global impact of tokens on the final output by accumulating local recurrences. We demonstrate that Simba outperforms the baseline model, Mamba, with the same FLOPS in various natural language tasks. Moreover, we illustrate the effect of highways, showing that Simba not only enhances efficiency but also improves the information flow across long sequences. Code is available at https://github.com/woominsong/Simba.

Related papers

• Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC [50.36542772932594]
  Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights.<n>In this work, we address the gap between training with full steps with low-rank projections (SVDLoRA) and LoRA fine-tuning.<n>We propose LoRSum, a memory-efficient subroutine that closes this gap for gradient descent.
  arXiv  Detail & Related papers  (2026-02-18T13:41:41Z)
• Sparse Layer Sharpness-Aware Minimization for Efficient Fine-Tuning [52.63618112418439]
  Sharpness-aware computation (SAM) seeks the minima with a flat loss landscape to improve the generalization performance in machine learning tasks, including fine-tuning.<n>We propose an approach SL-SAM to break this bottleneck by introducing the sparse technique to layers.
  arXiv  Detail & Related papers  (2026-02-10T04:05:43Z)
• The Curious Case of In-Training Compression of State Space Models [49.819321766705514]
  State Space Models (SSMs) tackle long sequence modeling tasks efficiently, offer both parallelizable training and fast inference.<n>Key design challenge is striking the right balance between maximizing expressivity and limiting this computational burden.<n>Our approach, textscCompreSSM, applies to Linear Time-Invariant SSMs such as Linear Recurrent Units, but is also extendable to selective models.
  arXiv  Detail & Related papers  (2025-10-03T09:02:33Z)
• StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning [31.585380521480868]
  We propose StruMamba3D, a novel paradigm for self-supervised point cloud representation learning.<n>We design spatial states and use them as proxies to preserve spatial dependencies among points.<n>Our method attains the SOTA 95.1% accuracy on ModelNet40 and 92.75% accuracy on the most challenging split of ScanObjectNN without voting strategy.
  arXiv  Detail & Related papers  (2025-06-26T17:58:05Z)
• SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot [8.080568103779893]
  State-space language models such as Mamba match Transformer quality while permitting linear complexity inference.<n>Existing one-shot pruning methods are tailored to attention blocks and fail to account for the time-shared and discretized state-transition matrix.<n>We introduce SparseSSM, the first training-free pruning framework that extends the classic optimal brain surgeon (OBS) framework to state space architectures.
  arXiv  Detail & Related papers  (2025-06-11T11:14:57Z)
• Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling [19.10832920407789]
  We introduce a new perspective by embedding the key principles of modern SSM directly into the Message-Passing Neural Network framework.<n>Our approach, MP-SSM, enables efficient, permutation-equivariant, and long-range information propagation while preserving the architectural simplicity of message passing.
  arXiv  Detail & Related papers  (2025-05-24T14:53:07Z)
• STree: Speculative Tree Decoding for Hybrid State-Space Models [46.17007054146938]
  Speculative decoding is a technique to leverage hardware to improve the efficiency of large-scale autoregressive (AR) Transformer models.<n>We propose the first scalable algorithm to perform tree-based speculative decoding in state-space models (SSMs) and hybrid architectures.
  arXiv  Detail & Related papers  (2025-05-20T23:12:16Z)
• Exploring Token Pruning in Vision State Space Models [38.122017567843905]
  State Space Models (SSMs) have the advantage of keeping linear computational complexity compared to attention modules in transformers. We take the novel step of enhancing the efficiency of SSM-based vision models through token-based pruning. We achieve 81.7% accuracy on ImageNet with a 41.6% reduction in the FLOPs for pruned PlainMamba-L3.
  arXiv  Detail & Related papers  (2024-09-27T17:59:50Z)
• SIGMA: Selective Gated Mamba for Sequential Recommendation [56.85338055215429]
  Mamba, a recent advancement, has exhibited exceptional performance in time series prediction.<n>We introduce a new framework named Selective Gated Mamba ( SIGMA) for Sequential Recommendation.<n>Our results indicate that SIGMA outperforms current models on five real-world datasets.
  arXiv  Detail & Related papers  (2024-08-21T09:12:59Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• SMR: State Memory Replay for Long Sequence Modeling [19.755738298836526]
  This paper proposes a novel non-recursive non-uniform sample processing strategy to overcome compatibility limitations in parallel convolutional computation. We introduce State Memory Replay (SMR), which utilizes learnable memories to adjust the current state with multi-step information for generalization at sampling points different from those in the training data. Experiments on long-range modeling tasks in autoregressive language modeling and Long Range Arena demonstrate the general effectiveness of the SMR mechanism for a series of SSM models.
  arXiv  Detail & Related papers  (2024-05-27T17:53:32Z)
• Submodular Reinforcement Learning [38.40138241424851]
  In reinforcement learning (RL), rewards of states are typically considered additive, and following the Markov assumption, they are $textitindependent$ states visited previously. In many important applications, such as coverage control, experiment design and informative path planning, rewards naturally have diminishing returns, i.e., their value decreases in light of similar states visited previously. We propose $textitsubmodular RL$ (SubRL), a paradigm which seeks to optimize more general, non-additive (and history-dependent) rewards modelled via submodular set functions which capture diminishing returns
  arXiv  Detail & Related papers  (2023-07-25T09:46:02Z)
• Efficient Long Sequence Modeling via State Space Augmented Transformer [92.74707853711374]
  We propose SPADE, short for $underlinetextbfS$tate sunderlinetextbfP$ace. We augment a SSM into the bottom layer of SPADE, and we employ efficient local attention methods for the other layers. Experimental results on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-12-15T20:51:27Z)
• Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks [88.77951448313486]
  We present a new approach for model acceleration by exploiting spatial sparsity in visual data. We propose a dynamic token sparsification framework to prune redundant tokens. We extend our method to hierarchical models including CNNs and hierarchical vision Transformers.
  arXiv  Detail & Related papers  (2022-07-04T17:00:51Z)
• Adaptive Recursive Circle Framework for Fine-grained Action Recognition [95.51097674917851]
  How to model fine-grained spatial-temporal dynamics in videos has been a challenging problem for action recognition. Most existing methods generate features of a layer in a pure feedforward manner. We propose an Adaptive Recursive Circle framework, a fine-grained decorator for pure feedforward layers.
  arXiv  Detail & Related papers  (2021-07-25T14:24:29Z)

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.