Small transformer architectures for task switching

• URL: http://arxiv.org/abs/2508.04461v1
• Date: Wed, 06 Aug 2025 14:01:05 GMT
• Title: Small transformer architectures for task switching
• Authors: Claudius Gros,
• Abstract summary: It is non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional approaches.<n>We show that standard transformers cannot solve a basic task switching reference model.<n>We show that transformers, long short-term memory recurrent networks (LSTM), and plain multi-layer perceptrons (MLPs) achieve similar, but only modest prediction accuracies.
• Score: 2.7195102129095003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional approaches, such as multi-layer perceptrons or recurrent networks. We examine this problem in the context of 'task switching'. In this framework models work on ongoing token sequences with the current task being determined by stochastically interspersed control tokens. We show that standard transformers cannot solve a basic task switching reference model based on finite domain arithmetics which contains subtasks dedicated to increment / addition / reverse copy / context (IARC). We show that transformers, long short-term memory recurrent networks (LSTM), and plain multi-layer perceptrons (MLPs) achieve similar, but only modest prediction accuracies. We enlarge our comparative study by including an extension of the standard transformer architecture to its non-translational invariant counterpart, the cisformer, and an alternative attention mechanism, extensive attention. A combination of the latter is found to be the only model able to achieve considerable performance levels, of around 95%. Our results indicate that the workings of attention can be understood better, and even improved, when comparing qualitatively different formulations in task-switching settings.

Related papers

• Is Attention Required for Transformer Inference? Explore Function-preserving Attention Replacement [13.38679135071682]
  We propose a Function-preserving Attention Replacement framework that replaces all attention blocks in pretrained transformers with learnable sequence-to-sequence modules.<n>We validate FAR on the DeiT vision transformer family and demonstrate that it matches the accuracy of the original models on ImageNet and multiple downstream tasks with reduced parameters and latency.
  arXiv  Detail & Related papers  (2025-05-24T02:23:46Z)
• Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction [29.12836710966048]
  We propose a novel transformer attention operator whose computational complexity scales linearly with the number of tokens.<n>Our results call into question the conventional wisdom that pairwise similarity style attention mechanisms are critical to the success of transformer architectures.
  arXiv  Detail & Related papers  (2024-12-23T18:59:21Z)
• Skip-Layer Attention: Bridging Abstract and Detailed Dependencies in Transformers [56.264673865476986]
  This paper introduces Skip-Layer Attention (SLA) to enhance Transformer models. SLA improves the model's ability to capture dependencies between high-level abstract features and low-level details. Our implementation extends the Transformer's functionality by enabling queries in a given layer to interact with keys and values from both the current layer and one preceding layer.
  arXiv  Detail & Related papers  (2024-06-17T07:24:38Z)
• NiNformer: A Network in Network Transformer with Token Mixing Generated Gating Function [1.3812010983144802]
  This paper introduces a new computational block as an alternative to the Vision Transformer ViT block.<n>The newly proposed block reduces the computational requirements by replacing the normal attention layers with a Network in Network structure.<n>It provides better performance than the baseline architectures on multiple datasets applied in the image classification task of the vision domain.
  arXiv  Detail & Related papers  (2024-03-04T19:08:20Z)
• Correlated Attention in Transformers for Multivariate Time Series [22.542109523780333]
  We propose a novel correlated attention mechanism, which efficiently captures feature-wise dependencies, and can be seamlessly integrated within the encoder blocks of existing Transformers. In particular, correlated attention operates across feature channels to compute cross-covariance matrices between queries and keys with different lag values, and selectively aggregate representations at the sub-series level. This architecture facilitates automated discovery and representation learning of not only instantaneous but also lagged cross-correlations, while inherently capturing time series auto-correlation.
  arXiv  Detail & Related papers  (2023-11-20T17:35:44Z)
• Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers [5.356051655680145]
  This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model. We substitute key elements of the attention mechanism in the Transformer with simple feed-forward networks, trained using the original components via knowledge distillation. Our experiments, conducted on the IWSLT 2017 dataset, reveal the capacity of these "attentionless Transformers" to rival the performance of the original architecture.
  arXiv  Detail & Related papers  (2023-11-17T16:58:52Z)
• FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification [53.55504611255664]
  FormerTime is a hierarchical representation model for improving the classification capacity for the multivariate time series classification task. It exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism.
  arXiv  Detail & Related papers  (2023-02-20T07:46:14Z)
• ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers [70.76313507550684]
  We propose a content-based sparse attention method, as an alternative to dense self-attention. Specifically, we cluster and then aggregate key and value tokens, as a content-based method of reducing the total token count. The resulting clustered-token sequence retains the semantic diversity of the original signal, but can be processed at a lower computational cost.
  arXiv  Detail & Related papers  (2022-08-28T04:18:27Z)
• Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution [50.10987776141901]
  Recent vision transformers along with self-attention have achieved promising results on various computer vision tasks. We introduce an effective hybrid architecture for super-resolution (SR) tasks, which leverages local features from CNNs and long-range dependencies captured by transformers. Our proposed method achieves state-of-the-art SR results on numerous benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-15T06:52:25Z)
• Less is More: Pay Less Attention in Vision Transformers [61.05787583247392]
  Less attention vIsion Transformer builds upon the fact that convolutions, fully-connected layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences. The proposed LIT achieves promising performance on image recognition tasks, including image classification, object detection and instance segmentation.
  arXiv  Detail & Related papers  (2021-05-29T05:26:07Z)
• Visual Saliency Transformer [127.33678448761599]
  We develop a novel unified model based on a pure transformer, Visual Saliency Transformer (VST), for both RGB and RGB-D salient object detection (SOD) It takes image patches as inputs and leverages the transformer to propagate global contexts among image patches. Experimental results show that our model outperforms existing state-of-the-art results on both RGB and RGB-D SOD benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-25T08:24:06Z)

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.