Understanding the Failure Modes of Transformers through the Lens of Graph Neural Networks

• URL: http://arxiv.org/abs/2512.09182v1
• Date: Tue, 09 Dec 2025 22:57:23 GMT
• Title: Understanding the Failure Modes of Transformers through the Lens of Graph Neural Networks
• Authors: Hunjae Lee,
• Abstract summary: This article is a study of many of the observed failure modes of transformers through the lens of graph neural network (GNN) theory.<n>We first make the case that much of deep learning, including transformers, is about learnable information mixing and propagation.<n>In addition, we analyze how the causal nature of decoder-only transformers create interesting geometric properties in information propagation, resulting in predictable and potentially devastating failure modes.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformers and more specifically decoder-only transformers dominate modern LLM architectures. While they have shown to work exceptionally well, they are not without issues, resulting in surprising failure modes and predictably asymmetric performance degradation. This article is a study of many of these observed failure modes of transformers through the lens of graph neural network (GNN) theory. We first make the case that much of deep learning, including transformers, is about learnable information mixing and propagation. This makes the study of model failure modes a study of bottlenecks in information propagation. This naturally leads to GNN theory, where there is already a rich literature on information propagation bottlenecks and theoretical failure modes of models. We then make the case that many issues faced by GNNs are also experienced by transformers. In addition, we analyze how the causal nature of decoder-only transformers create interesting geometric properties in information propagation, resulting in predictable and potentially devastating failure modes. Finally, we observe that existing solutions in transformer research tend to be ad-hoc and driven by intuition rather than grounded theoretical motivation. As such, we unify many such solutions under a more theoretical perspective, providing insight into why they work, what problem they are actually solving, and how they can be further improved to target specific failure modes of transformers. Overall, this article is an attempt to bridge the gap between observed failure modes in transformers and a general lack of theoretical understanding of them in this space.

Related papers

• Transformers for Learning on Noisy and Task-Level Manifolds: Approximation and Generalization Insights [47.62295798627317]
  This work establishes a theoretical foundation by analyzing the performance of transformers for regression tasks involving noisy input data on a manifold.<n>We prove approximation and generalization errors which crucially depend on the intrinsic dimension of the manifold.<n>Our results demonstrate that transformers can leverage low-complexity structures in learning task even when the input data are perturbed by high-dimensional noise.
  arXiv  Detail & Related papers  (2025-05-06T05:41:46Z)
• 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)
• Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization [88.5582111768376]
  We study the optimization of a Transformer composed of a self-attention layer with softmax followed by a fully connected layer under gradient descent on a certain data distribution model. Our results establish a sharp condition that can distinguish between the small test error phase and the large test error regime, based on the signal-to-noise ratio in the data model.
  arXiv  Detail & Related papers  (2024-09-28T13:24:11Z)
• How Transformers Learn Causal Structure with Gradient Descent [44.31729147722701]
  Self-attention allows transformers to encode causal structure. We introduce an in-context learning task that requires learning latent causal structure. We show that transformers trained on our in-context learning task are able to recover a wide variety of causal structures.
  arXiv  Detail & Related papers  (2024-02-22T17:47:03Z)
• Setting the Record Straight on Transformer Oversmoothing [35.125957267464756]
  As model depth increases, Transformers oversmooth, i.e., inputs become more and more similar. We show that smoothing behavior depends on the eigenspectrum of the value and projection weights. Our analysis reveals a simple way to parameterize the weights of the Transformer update equations to influence smoothing behavior.
  arXiv  Detail & Related papers  (2024-01-09T01:19:03Z)
• Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation [105.22961467028234]
  Skip connections and normalisation layers are ubiquitous for the training of Deep Neural Networks (DNNs) Recent approaches such as Deep Kernel Shaping have made progress towards reducing our reliance on them. But these approaches are incompatible with the self-attention layers present in transformers.
  arXiv  Detail & Related papers  (2023-02-20T21:26:25Z)
• Attention Enables Zero Approximation Error [22.110336842946555]
  We show that a single-head self-attention transformer with a fixed number of transformer encoder blocks and free parameters is able to generate any desired encoder of the input with no error. As a direct consequence, we show that the single-head self-attention transformer with increasing numbers of free parameters is universal.
  arXiv  Detail & Related papers  (2022-02-24T16:06:01Z)
• On the Power of Saturated Transformers: A View from Circuit Complexity [87.20342701232869]
  We show that saturated transformers transcend the limitations of hard-attention transformers. The jump from hard to saturated attention can be understood as increasing the transformer's effective circuit depth by a factor of $O(log n)$.
  arXiv  Detail & Related papers  (2021-06-30T17:09:47Z)
• 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.