ParaFormer: Shallow Parallel Transformers with Progressive Approximation

• URL: http://arxiv.org/abs/2510.15425v1
• Date: Fri, 17 Oct 2025 08:28:26 GMT
• Title: ParaFormer: Shallow Parallel Transformers with Progressive Approximation
• Abstract summary: ParaFormer is a shallow Transformer architecture designed for true parallelism in both structure and computation.<n>Our theoretical analysis shows that their performance relies on inter-layer collaboration for progressive approximation, rather than depth itself.<n>ParaFormer supports up to 15.07x model compression and facilitates model expansion for adaptive continuous learning.
• Score: 14.82319078008725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The widespread 'deeper is better' philosophy has driven the creation of architectures like ResNet and Transformer, which achieve high performance by stacking numerous layers. However, increasing model depth comes with challenges such as longer training times, higher inference latency, and impracticality on resource-constrained devices. To address these issues, we propose ParaFormer, a shallow Transformer architecture designed for true parallelism in both structure and computation. By formulating standard Transformers as function approximators in closed-form, our theoretical analysis shows that their performance relies on inter-layer collaboration for progressive approximation, rather than depth itself. While deep Transformers enforce this collaboration through sequential designs, we demonstrate that such collaboration is not inherently tied to sequential structures. ParaFormer removes the sequential constraint by organizing layers into parallel branches, enforcing inter-layer collaboration algorithmically. Specifically, we implement progressive approximation, ensuring that each new branch further reduces the loss from preceding branches, enabling faster convergence. Extensive experiments validate ParaFormer's effectiveness, outperforming standard Transformers like ViT. Moreover, ParaFormer supports up to 15.07x model compression and facilitates model expansion for adaptive continuous learning. Experimental results on multi-GPU deployment demonstrate that ParaFormer is 3.30x faster than widely used parallelism solutions such as FairScale. These advancements stem from our closed-form formulation of Transformers based on the Universal Approximation Theorem, which not only explains the ``depth belief'' but also opens new avenues for designing efficient Transformer architectures. Source code: https://(open-upon-acceptance)

Related papers

• Déjà View: Looping Transformers for Multi-View 3D Reconstruction [109.98721386523641]
  Recent feed-forward 3D reconstruction transformers have scaled to over a billion parameters.<n>We show that model depth partially buys iteration, paid for inefficiently in unique parameters, and instead make that iteration explicit in architecture.<n>Our model, DéjView, applies a single looped transformer block recurrently to per-view features for K refinement steps.
  arXiv  Detail & Related papers  (2026-05-28T16:47:48Z)
• RubiConv -- Efficient Boundary-Respecting Convolutions [16.714478912341708]
  We develop a novel algorithm for performing hardware-efficient, boundary-respecting convolutions on packed sequences.<n>RubiConv achieves significant speedups over both attention and standard FFT-based baselines.
  arXiv  Detail & Related papers  (2026-05-08T20:17:12Z)
• Rethinking Vision Transformer Depth via Structural Reparameterization [16.12815682992294]
  We propose a branch-based structural reparameterization technique that operates during the training phase.<n>Our approach leverages parallel branches within transformer blocks that can be systematically consolidated into streamlined single-path models.<n>When applied to ViT-Tiny, the framework successfully reduces the original 12-layer architecture to 6, 4, or as few as 3 layers while maintaining classification accuracy on ImageNet-1K.
  arXiv  Detail & Related papers  (2025-11-24T21:28:55Z)
• DeepCoT: Deep Continual Transformers for Real-Time Inference on Data Streams [63.27233749591346]
  Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks.<n>Stream data inference is typically performed over a sliding temporal window, leading to highly redundant computations.<n>We propose the Deep Continual Transformer (DeepCoT), a redundancy-free encoder-only model that can be applied over existing deep encoder architectures with minimal changes.
  arXiv  Detail & Related papers  (2025-11-21T16:15:43Z)
• ScaleFormer: Span Representation Cumulation for Long-Context Transformer [9.845891949404534]
  We propose a plug-and-play framework that adapts off-the-shelf pre-trained encoder-decoder models to process long sequences.<n>Our approach segments long inputs into overlapping chunks and generates a compressed, context-aware representation for the decoder.<n> Experiments on long-document summarization show that our method is highly competitive with and often outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-11-13T07:05:45Z)
• PiT: Progressive Diffusion Transformer [50.46345527963736]
  Diffusion Transformers (DiTs) achieve remarkable performance within image generation via the transformer architecture.<n>We find that DiTs do not rely as heavily on global information as previously believed.<n>We propose a series of Pseudo Progressive Diffusion Transformer (PiT)
  arXiv  Detail & Related papers  (2025-05-19T15:02:33Z)
• TinyFusion: Diffusion Transformers Learned Shallow [52.96232442322824]
  Diffusion Transformers have demonstrated remarkable capabilities in image generation but often come with excessive parameterization.<n>We present TinyFusion, a depth pruning method designed to remove redundant layers from diffusion transformers via end-to-end learning.<n>Experiments with DiT-XL show that TinyFusion can craft a shallow diffusion transformer at less than 7% of the pre-training cost, achieving a 2$times$ speedup with an FID score of 2.86.
  arXiv  Detail & Related papers  (2024-12-02T07:05:39Z)
• Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning? [69.4145579827826]
  We show a fast flow on the regression loss despite the gradient non-ity algorithms for our convergence landscape. This is the first theoretical analysis for multi-layer Transformer in this setting.
  arXiv  Detail & Related papers  (2024-10-10T18:29:05Z)
• Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference [8.527031391688283]
  Kraken is an evolution of the standard Transformer architecture for efficient inference on multi-device systems. When trained on OpenWebText, Kraken models reach a similar perplexity as standard Transformers. When tested on the SuperGLUE benchmark, Kraken speeds up Time To First Token by a mean of 35.6% across a range of model sizes.
  arXiv  Detail & Related papers  (2024-08-14T20:24:03Z)
• Aligning Transformers with Weisfeiler-Leman [5.0452971570315235]
  Graph neural network architectures aligned with the $k$-WL hierarchy offer theoretically well-understood expressive power. We develop a theoretical framework that allows the study of established positional encodings such as Laplacian PEs and SPE. We evaluate our transformers on the large-scale PCQM4Mv2 dataset, showing competitive predictive performance with the state-of-the-art.
  arXiv  Detail & Related papers  (2024-06-05T11:06:33Z)
• Transformer Fusion with Optimal Transport [25.022849817421964]
  Fusion is a technique for merging multiple independently-trained neural networks in order to combine their capabilities. This paper presents a systematic approach for fusing two or more transformer-based networks exploiting Optimal Transport to (soft-)align the various architectural components.
  arXiv  Detail & Related papers  (2023-10-09T13:40:31Z)
• Make Deep Networks Shallow Again [6.647569337929869]
  A breakthrough has been achieved by the concept of residual connections. A stack of residual connection layers can be expressed as an expansion of terms similar to the Taylor expansion. In other words, a sequential deep architecture is substituted by a parallel shallow one.
  arXiv  Detail & Related papers  (2023-09-15T14:18:21Z)
• Full Stack Optimization of Transformer Inference: a Survey [58.55475772110702]
  Transformer models achieve superior accuracy across a wide range of applications. The amount of compute and bandwidth required for inference of recent Transformer models is growing at a significant rate. There has been an increased focus on making Transformer models more efficient.
  arXiv  Detail & Related papers  (2023-02-27T18:18:13Z)
• Softmax-free Linear Transformers [90.83157268265654]
  Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. Existing methods are either theoretically flawed or empirically ineffective for visual recognition. We propose a family of Softmax-Free Transformers (SOFT)
  arXiv  Detail & Related papers  (2022-07-05T03:08:27Z)
• Finetuning Pretrained Transformers into RNNs [81.72974646901136]
  Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. A linear-complexity recurrent variant has proven well suited for autoregressive generation. This work aims to convert a pretrained transformer into its efficient recurrent counterpart.
  arXiv  Detail & Related papers  (2021-03-24T10:50:43Z)

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.