CATFormer: When Continual Learning Meets Spiking Transformers With Dynamic Thresholds

• URL: http://arxiv.org/abs/2603.15184v1
• Date: Mon, 16 Mar 2026 12:20:23 GMT
• Title: CATFormer: When Continual Learning Meets Spiking Transformers With Dynamic Thresholds
• Abstract summary: Existing spiking neural networks (SNNs) for class-incremental learning (CIL) suffer a sharp performance drop as tasks accumulate.<n>We here introduce CATFormer, a scalable framework that overcomes this limitation.<n>We observe that the key to preventing forgetting in SNNs lies not only in synaptic plasticity but also in modulating neuronal excitability.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although deep neural networks perform extremely well in controlled environments, they fail in real-world scenarios where data isn't available all at once, and the model must adapt to a new data distribution that may or may not follow the initial distribution. Previously acquired knowledge is lost during subsequent updates based on new data. a phenomenon commonly known as catastrophic forgetting. In contrast, the brain can learn without such catastrophic forgetting, irrespective of the number of tasks it encounters. Existing spiking neural networks (SNNs) for class-incremental learning (CIL) suffer a sharp performance drop as tasks accumulate. We here introduce CATFormer (Context Adaptive Threshold Transformer), a scalable framework that overcomes this limitation. We observe that the key to preventing forgetting in SNNs lies not only in synaptic plasticity but also in modulating neuronal excitability. At the core of CATFormer is the Dynamic Threshold Leaky Integrate-and-Fire (DTLIF) neuron model, which leverages context-adaptive thresholds as the primary mechanism for knowledge retention. This is paired with a Gated Dynamic Head Selection (G-DHS) mechanism for task-agnostic inference. Extensive evaluation on both static (CIFAR-10/100/Tiny-ImageNet) and neuromorphic (CIFAR10-DVS/SHD) datasets reveals that CATFormer outperforms existing rehearsal-free CIL algorithms across various task splits, establishing it as an ideal architecture for energy-efficient, true-class incremental learning.

Related papers

• SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network [19.73335869722781]
  Continuous learning of novel classes is crucial for edge devices to preserve data privacy and maintain reliable performance in dynamic environments.<n>In this work, we present an SNN-based method for On-Device FSCIL ie., Sparsity-Aware and Fast Adaptive SNN.
  arXiv  Detail & Related papers  (2025-10-04T03:21:31Z)
• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• ALADE-SNN: Adaptive Logit Alignment in Dynamically Expandable Spiking Neural Networks for Class Incremental Learning [15.022211557367273]
  We develop spiking neural networks (SNNs) with dynamic structures for Class Incremental Learning (CIL)<n>We propose the ALADE-SNN framework, which includes adaptive logit alignment for balanced feature representation and OtoN suppression to manage weights mapping frozen old features to new classes during training.<n>Experiment results show that ALADE-SNN achieves an average incremental accuracy of 75.42 on the CIFAR100-B0 benchmark over 10 incremental steps.
  arXiv  Detail & Related papers  (2024-12-17T09:13:22Z)
• Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning [38.09011520275557]
  Class-incremental learning (CIL) aims to train a model to learn new classes from non-stationary data streams without forgetting old ones. We propose a new kind of connectionist model by tailoring neural unit dynamics that adapt the behavior of neural networks for CIL.
  arXiv  Detail & Related papers  (2024-06-04T15:47:03Z)
• How neural networks learn to classify chaotic time series [77.34726150561087]
  We study the inner workings of neural networks trained to classify regular-versus-chaotic time series. We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
  arXiv  Detail & Related papers  (2023-06-04T08:53:27Z)
• Understanding and Improving Transfer Learning of Deep Models via Neural Collapse [37.483109067209504]
  This work investigates the relationship between neural collapse (NC) and transfer learning for classification problems. We find strong correlation between feature collapse and downstream performance. Our proposed fine-tuning methods deliver good performances while reducing fine-tuning parameters by at least 90%.
  arXiv  Detail & Related papers  (2022-12-23T08:48:34Z)
• Neural Attentive Circuits [93.95502541529115]
  We introduce a general purpose, yet modular neural architecture called Neural Attentive Circuits (NACs) NACs learn the parameterization and a sparse connectivity of neural modules without using domain knowledge. NACs achieve an 8x speedup at inference time while losing less than 3% performance.
  arXiv  Detail & Related papers  (2022-10-14T18:00:07Z)
• Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation [70.75043144299168]
  Spiking Neural Network (SNN) is a promising energy-efficient AI model when implemented on neuromorphic hardware. It is a challenge to efficiently train SNNs due to their non-differentiability. We propose the Differentiation on Spike Representation (DSR) method, which could achieve high performance.
  arXiv  Detail & Related papers  (2022-05-01T12:44:49Z)
• Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay [67.50637511633212]
  A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents that adapt is that neural systems struggle to retain previously-acquired knowledge when learning from new samples. This problem is known as catastrophic forgetting (interference) and remains an unsolved problem in the domain of machine learning to this day.
  arXiv  Detail & Related papers  (2021-12-09T07:11:14Z)
• Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems [24.0378100479104]
  Recurrent neural networks (RNNs) are powerful models for processing time-series data. The framework of reverse engineering a trained RNN by linearizing around its fixed points has provided insight, but the approach has significant challenges. We present a new model that overcomes these limitations by co-training an RNN with a novel switching linear dynamical system (SLDS) formulation.
  arXiv  Detail & Related papers  (2021-11-01T20:49:30Z)
• SpaceNet: Make Free Space For Continual Learning [15.914199054779438]
  We propose a novel architectural-based method referred as SpaceNet for class incremental learning scenario. SpaceNet trains sparse deep neural networks from scratch in an adaptive way that compresses the sparse connections of each task in a compact number of neurons. Experimental results show the robustness of our proposed method against catastrophic forgetting old tasks and the efficiency of SpaceNet in utilizing the available capacity of the model.
  arXiv  Detail & Related papers  (2020-07-15T11:21:31Z)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)

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.