Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers

• URL: http://arxiv.org/abs/2407.11542v3
• Date: Tue, 20 May 2025 11:40:37 GMT
• Title: Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers
• Authors: Freya Behrens, Luca Biggio, Lenka Zdeborová,
• Abstract summary: We analyze the solutions simple transformer blocks implement when tackling the histogram task.<n>This task reveals a complex interplay between predictive performance, vocabulary and embedding sizes, token-mixing mechanisms, and feed-forward layer capacity.
• Score: 16.26331213222281
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Next to scaling considerations, architectural design choices profoundly shape the solution space of transformers. In this work, we analyze the solutions simple transformer blocks implement when tackling the histogram task: counting items in sequences. Despite its simplicity, this task reveals a complex interplay between predictive performance, vocabulary and embedding sizes, token-mixing mechanisms, and feed-forward layer capacity. We identify two theoretical counting strategies transformers adopt, relation-based and inventory-based counting, each defining distinct learning regimes for the task. These strategies dictate how functionality is distributed between attention and feed-forward layers. We further show that adding softmax and beginning-of-sequence tokens allow for more robustness when embedding dimensions are comparatively small. Empirical introspection of trained models closely confirms both the learning regimes of the various architectures and the formation of these strategies during training. We demonstrate how a basic task that requires only aggregation and selection is significantly impacted by minor design changes.

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)
• The Morphology-Control Trade-Off: Insights into Soft Robotic Efficiency [15.273412572397799]
  In this study, we investigate the interplay between morphological and control complexities and their collective impact on task performance. Results show that optimal performance depends on the alignment between morphology and control. This study contributes to the practical application of soft robotics in real-world scenarios.
  arXiv  Detail & Related papers  (2025-03-20T13:19:54Z)
• Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers [10.206921909332006]
  This study investigates the internal mechanisms underlying Transformers' behavior in compositional tasks. We find that complexity control strategies influence whether the model learns primitive-level rules that generalize out-of-distribution (reasoning-based solutions) or relies solely on memorized mappings (memory-based solutions)
  arXiv  Detail & Related papers  (2025-01-15T02:54:52Z)
• Interpreting token compositionality in LLMs: A robustness analysis [10.777646083061395]
  Constituent-Aware Pooling (CAP) is a methodology designed to analyse how large language models process linguistic structures. CAP intervenes in model activations through constituent-based pooling at various model levels.
  arXiv  Detail & Related papers  (2024-10-16T18:10:50Z)
• Dynamical Mean-Field Theory of Self-Attention Neural Networks [0.0]
  Transformer-based models have demonstrated exceptional performance across diverse domains. Little is known about how they operate or what are their expected dynamics. We use methods for the study of asymmetric Hopfield networks in nonequilibrium regimes.
  arXiv  Detail & Related papers  (2024-06-11T13:29:34Z)
• Initialization is Critical to Whether Transformers Fit Composite Functions by Inference or Memorizing [10.206921909332006]
  Transformers have shown impressive capabilities across various tasks, but their performance on compositional problems remains a topic of debate. In this work, we investigate the mechanisms of how transformers behave on unseen compositional tasks.
  arXiv  Detail & Related papers  (2024-05-08T20:23:24Z)
• Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence [51.54175067684008]
  This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. We first show that feature aggregation and cost aggregation exhibit distinct characteristics and reveal the potential for substantial benefits stemming from the judicious use of both aggregation processes. Our framework is evaluated on standard benchmarks for semantic matching, and also applied to geometric matching, where we show that our approach achieves significant improvements compared to existing methods.
  arXiv  Detail & Related papers  (2024-03-17T07:02:55Z)
• Task Indicating Transformer for Task-conditional Dense Predictions [16.92067246179703]
  We introduce a novel task-conditional framework called Task Indicating Transformer (TIT) to tackle this challenge. Our approach designs a Mix Task Adapter module within the transformer block, which incorporates a Task Indicating Matrix through matrix decomposition. We also propose a Task Gate Decoder module that harnesses a Task Indicating Vector and gating mechanism to facilitate adaptive multi-scale feature refinement.
  arXiv  Detail & Related papers  (2024-03-01T07:06:57Z)
• Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers [13.480259378415505]
  BiXT scales linearly with input size in terms of computational cost and memory consumption. BiXT is inspired by the Perceiver architectures but replaces iterative attention with an efficient bi-directional cross-attention module. By combining efficiency with the generality and performance of a full Transformer architecture, BiXT can process longer sequences.
  arXiv  Detail & Related papers  (2024-02-19T13:38:15Z)
• How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations [98.7450564309923]
  This paper takes initial steps on understanding in-context learning (ICL) in more complex scenarios, by studying learning with representations. We construct synthetic in-context learning problems with a compositional structure, where the label depends on the input through a possibly complex but fixed representation function. We show theoretically the existence of transformers that approximately implement such algorithms with mild depth and size.
  arXiv  Detail & Related papers  (2023-10-16T17:40:49Z)
• Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection [88.23337313766353]
  This work first provides a comprehensive statistical theory for transformers to perform ICL. We show that transformers can implement a broad class of standard machine learning algorithms in context. A emphsingle transformer can adaptively select different base ICL algorithms.
  arXiv  Detail & Related papers  (2023-06-07T17:59:31Z)
• Faith and Fate: Limits of Transformers on Compositionality [109.79516190693415]
  We investigate the limits of transformer large language models across three representative compositional tasks. These tasks require breaking problems down into sub-steps and synthesizing these steps into a precise answer. Our empirical findings suggest that transformer LLMs solve compositional tasks by reducing multi-step compositional reasoning into linearized subgraph matching.
  arXiv  Detail & Related papers  (2023-05-29T23:24:14Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• Systematic Generalization and Emergent Structures in Transformers Trained on Structured Tasks [6.525090891505941]
  We show how a causal transformer can perform a set of algorithmic tasks, including copying, sorting, and hierarchical compositions. We show that two-layer transformers learn generalizable solutions to multi-level problems and develop signs of systematic task decomposition. These results provide key insights into how transformer models may be capable of decomposing complex decisions into reusable, multi-level policies.
  arXiv  Detail & Related papers  (2022-10-02T00:46:36Z)
• 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)
• Unveiling Transformers with LEGO: a synthetic reasoning task [23.535488809197787]
  We study how the transformer architecture learns to follow a chain of reasoning. In some data regime the trained transformer finds "shortcut" solutions to follow the chain of reasoning. We find that one can prevent such shortcut with appropriate architecture modification or careful data preparation.
  arXiv  Detail & Related papers  (2022-06-09T06:30:17Z)
• Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization [101.72755769194677]
  We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph. Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks. Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
  arXiv  Detail & Related papers  (2022-05-25T10:44:25Z)
• 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)
• Scalable Gaussian Processes for Data-Driven Design using Big Data with Categorical Factors [14.337297795182181]
  Gaussian processes (GP) have difficulties in accommodating big datasets, categorical inputs, and multiple responses. We propose a GP model that utilizes latent variables and functions obtained through variational inference to address the aforementioned challenges simultaneously. Our approach is demonstrated for machine learning of ternary oxide materials and topology optimization of a multiscale compliant mechanism.
  arXiv  Detail & Related papers  (2021-06-26T02:17:23Z)
• Few-shot Sequence Learning with Transformers [79.87875859408955]
  Few-shot algorithms aim at learning new tasks provided only a handful of training examples. In this work we investigate few-shot learning in the setting where the data points are sequences of tokens. We propose an efficient learning algorithm based on Transformers.
  arXiv  Detail & Related papers  (2020-12-17T12:30:38Z)
• CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning [138.40338621974954]
  CausalWorld is a benchmark for causal structure and transfer learning in a robotic manipulation environment. Tasks consist of constructing 3D shapes from a given set of blocks - inspired by how children learn to build complex structures.
  arXiv  Detail & Related papers  (2020-10-08T23:01:13Z)
• A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention [96.77554122595578]
  We introduce a parametrized representation of fixed size, which embeds and then aggregates elements from a given input set according to the optimal transport plan between the set and a trainable reference. Our approach scales to large datasets and allows end-to-end training of the reference, while also providing a simple unsupervised learning mechanism with small computational cost.
  arXiv  Detail & Related papers  (2020-06-22T08:35:58Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

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.