Attention-Only Transformers via Unrolled Subspace Denoising

• URL: http://arxiv.org/abs/2506.03790v1
• Date: Wed, 04 Jun 2025 09:53:14 GMT
• Title: Attention-Only Transformers via Unrolled Subspace Denoising
• Authors: Peng Wang, Yifu Lu, Yaodong Yu, Druv Pai, Qing Qu, Yi Ma,
• Abstract summary: We derive a fully interpretable transformer architecture with only necessary components.<n>By unrolling such iterative denoising operations into a deep network, we arrive at a highly compact architecture.<n>Despite its simplicity, experiments on vision and language tasks demonstrate that such a transformer achieves performance close to that of standard transformer architectures.
• Score: 19.832264029213515
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer architectures may be redundant. To derive a fully interpretable transformer architecture with only necessary components, we contend that the goal of representation learning is to compress a set of noisy initial token representations towards a mixture of low-dimensional subspaces. To compress these noisy token representations, an associated denoising operation naturally takes the form of a multi-head (subspace) self-attention. By unrolling such iterative denoising operations into a deep network, we arrive at a highly compact architecture that consists of \textit{only} self-attention operators with skip connections at each layer. Moreover, we show that each layer performs highly efficient denoising: it improves the signal-to-noise ratio of token representations \textit{at a linear rate} with respect to the number of layers. Despite its simplicity, extensive experiments on vision and language tasks demonstrate that such a transformer achieves performance close to that of standard transformer architectures such as GPT-2 and CRATE.

Related papers

• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space.<n>Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators [83.48423407316713]
  We present a novel diffusion transformer framework incorporating an additional set of mediator tokens to engage with queries and keys separately. Our model initiates the denoising process with a precise, non-ambiguous stage and gradually transitions to a phase enriched with detail. Our method achieves a state-of-the-art FID score of 2.01 when integrated with the recent work SiT.
  arXiv  Detail & Related papers  (2024-08-11T07:01:39Z)
• Mesh Denoising Transformer [104.5404564075393]
  Mesh denoising is aimed at removing noise from input meshes while preserving their feature structures. SurfaceFormer is a pioneering Transformer-based mesh denoising framework. New representation known as Local Surface Descriptor captures local geometric intricacies. Denoising Transformer module receives the multimodal information and achieves efficient global feature aggregation.
  arXiv  Detail & Related papers  (2024-05-10T15:27:43Z)
• White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? [27.58916930770997]
  We show a family of white-box transformer-like deep network architectures, named CRATE, which are mathematically fully interpretable. Experiments show that these networks, despite their simplicity, indeed learn to compress and sparsify representations of large-scale real-world image and text datasets.
  arXiv  Detail & Related papers  (2023-11-22T02:23:32Z)
• White-Box Transformers via Sparse Rate Reduction [25.51855431031564]
  We show a family of white-box transformer-like deep network architectures which are mathematically fully interpretable. Experiments show that these networks indeed learn to optimize the designed objective.
  arXiv  Detail & Related papers  (2023-06-01T20:28:44Z)
• DDT: Dual-branch Deformable Transformer for Image Denoising [6.596462333804802]
  Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome limitations presented by inductive convolutional biases. We propose an efficient Dual-branch Deformable Transformer (DDT) denoising network which captures both local and global interactions in parallel.
  arXiv  Detail & Related papers  (2023-04-13T08:54:44Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Combiner: Full Attention Transformer with Sparse Computation Cost [142.10203598824964]
  We propose Combiner, which provides full attention capability in each attention head while maintaining low computation complexity. We show that most sparse attention patterns used in existing sparse transformers are able to inspire the design of such factorization for full attention. An experimental evaluation on both autoregressive and bidirectional sequence tasks demonstrates the effectiveness of this approach.
  arXiv  Detail & Related papers  (2021-07-12T22:43:11Z)
• Transformers Solve the Limited Receptive Field for Monocular Depth Prediction [82.90445525977904]
  We propose TransDepth, an architecture which benefits from both convolutional neural networks and transformers. This is the first paper which applies transformers into pixel-wise prediction problems involving continuous labels.
  arXiv  Detail & Related papers  (2021-03-22T18:00:13Z)

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.