Noradrenergic-inspired gain modulation attenuates the stability gap in joint training

• URL: http://arxiv.org/abs/2507.14056v1
• Date: Fri, 18 Jul 2025 16:34:06 GMT
• Title: Noradrenergic-inspired gain modulation attenuates the stability gap in joint training
• Authors: Alejandro Rodriguez-Garcia, Anindya Ghosh, Srikanth Ramaswamy,
• Abstract summary: Studies in continual learning have identified a transient drop in performance on mastered tasks when assimilating new ones, known as the stability gap.<n>We argue that it reflects an imbalance between rapid adaptation and robust retention at task boundaries.<n>Inspired by locus coeruleus mediated noradrenergic bursts, we propose uncertainty-modulated gain dynamics.
• Score: 44.99833362998488
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent studies in continual learning have identified a transient drop in performance on mastered tasks when assimilating new ones, known as the stability gap. Such dynamics contradict the objectives of continual learning, revealing a lack of robustness in mitigating forgetting, and notably, persisting even under an ideal joint-loss regime. Examining this gap within this idealized joint training context is critical to isolate it from other sources of forgetting. We argue that it reflects an imbalance between rapid adaptation and robust retention at task boundaries, underscoring the need to investigate mechanisms that reconcile plasticity and stability within continual learning frameworks. Biological brains navigate a similar dilemma by operating concurrently on multiple timescales, leveraging neuromodulatory signals to modulate synaptic plasticity. However, artificial networks lack native multitimescale dynamics, and although optimizers like momentum-SGD and Adam introduce implicit timescale regularization, they still exhibit stability gaps. Inspired by locus coeruleus mediated noradrenergic bursts, which transiently enhance neuronal gain under uncertainty to facilitate sensory assimilation, we propose uncertainty-modulated gain dynamics - an adaptive mechanism that approximates a two-timescale optimizer and dynamically balances integration of knowledge with minimal interference on previously consolidated information. We evaluate our mechanism on domain-incremental and class-incremental variants of the MNIST and CIFAR benchmarks under joint training, demonstrating that uncertainty-modulated gain dynamics effectively attenuate the stability gap. Finally, our analysis elucidates how gain modulation replicates noradrenergic functions in cortical circuits, offering mechanistic insights into reducing stability gaps and enhance performance in continual learning tasks.

Related papers

• LyAm: Robust Non-Convex Optimization for Stable Learning in Noisy Environments [0.0]
  Training deep neural networks, particularly in computer vision tasks, often suffers from noisy gradients.<n>We propose LyAm, a novel that integrates Adam's adaptive moment estimation with Lyapunov-based stability mechanisms.<n>LyAm consistently outperforms state-of-the-art settings in terms of accuracy, convergence, speed, and stability.
  arXiv  Detail & Related papers  (2025-07-15T12:35:13Z)
• Continual Learning in Vision-Language Models via Aligned Model Merging [84.47520899851557]
  We present a new perspective based on model merging to maintain stability while still retaining plasticity.<n>To maximize the effectiveness of the merging process, we propose a simple mechanism that promotes learning aligned weights with previous ones.
  arXiv  Detail & Related papers  (2025-05-30T20:52:21Z)
• Spiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning [32.60363000758323]
  We propose a temporal attention-guided adaptive fusion framework for multimodal spiking neural networks (SNNs)<n>The proposed framework implements adaptive fusion, especially in the temporal dimension, and alleviates the modality imbalance during multimodal learning.<n>The system resolves temporal misalignment through learnable time-warping operations and faster modality convergence coordination than baseline SNNs.
  arXiv  Detail & Related papers  (2025-05-20T15:55:11Z)
• Generative System Dynamics in Recurrent Neural Networks [56.958984970518564]
  We investigate the continuous time dynamics of Recurrent Neural Networks (RNNs)<n>We show that skew-symmetric weight matrices are fundamental to enable stable limit cycles in both linear and nonlinear configurations.<n> Numerical simulations showcase how nonlinear activation functions not only maintain limit cycles, but also enhance the numerical stability of the system integration process.
  arXiv  Detail & Related papers  (2025-04-16T10:39:43Z)
• Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration [28.75006029656076]
  In this paper, we introduce SSDE, a novel structure-based approach that enhances plasticity through a fine-grained allocation strategy.<n>SSDE decomposes the parameter space into forward-transfer (frozen) parameters and task-specific (trainable) parameters.<n>Experiments on the CW10-v1 Continual World benchmark demonstrate that SSDE achieves state-of-the-art performance, reaching a success rate of 95%.
  arXiv  Detail & Related papers  (2025-03-07T08:58:07Z)
• Unconditional stability of a recurrent neural circuit implementing divisive normalization [0.0]
  We prove the remarkable property of unconditional local stability for an arbitrary-dimensional ORGaNICs circuit.<n>We show that ORGaNICs can be trained by backpropagation through time without gradient clipping/scaling.
  arXiv  Detail & Related papers  (2024-09-27T17:46:05Z)
• Neural Interaction Energy for Multi-Agent Trajectory Prediction [55.098754835213995]
  We introduce a framework called Multi-Agent Trajectory prediction via neural interaction Energy (MATE) MATE assesses the interactive motion of agents by employing neural interaction energy. To bolster temporal stability, we introduce two constraints: inter-agent interaction constraint and intra-agent motion constraint.
  arXiv  Detail & Related papers  (2024-04-25T12:47:47Z)
• Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence [59.11038175596807]
  Continual learning aims to empower artificial intelligence with strong adaptability to the real world. Existing advances mainly focus on preserving memory stability to overcome catastrophic forgetting. We propose a generic approach that appropriately attenuates old memories in parameter distributions to improve learning plasticity.
  arXiv  Detail & Related papers  (2023-08-29T02:43:58Z)
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations [54.23691425062034]
  We study the continuous-time dynamics induced by GAN training. From this perspective, we hypothesise that instabilities in training GANs arise from the integration error. We experimentally verify that well-known ODE solvers (such as Runge-Kutta) can stabilise training.
  arXiv  Detail & Related papers  (2020-10-28T15:23:49Z)

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.