Heterogeneous Knowledge Distillation via Geometry Decoupling and Momentum-Aware Gradient Regulation

• URL: http://arxiv.org/abs/2606.24557v1
• Date: Tue, 23 Jun 2026 13:23:58 GMT
• Title: Heterogeneous Knowledge Distillation via Geometry Decoupling and Momentum-Aware Gradient Regulation
• Abstract summary: SPOFA is a framework built upon a novel Feature and Gradient Dual Stabilization mechanism.<n>MEMA actively evaluates instantaneous gradient conflicts and adaptively penalizes harmful distillation signals.<n>Experiments on two mainstream benchmarks demonstrate that SPOFA achieves state-of-the-art accuracy.
• Score: 3.619179880246355
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Heterogeneous Knowledge Distillation (HKD) aims to transfer knowledge across varying architectures (e.g., from Transformer to CNN) but inherently suffers from severe training instability. We reveal that this instability stems from two highly coupled challenges: massive feature norm discrepancies that cause optimization drag, and severe gradient conflicts between the primary and distillation objectives arising from distinct inductive biases. To achieve stable distillation, we propose SPOFA, a framework built upon a novel Feature and Gradient Dual Stabilization mechanism. Specifically, at the feature level, we introduce a LayerNorm-based decoupling projector that explicitly decouples feature magnitude from direction, creating a bounded and stable space for semantic alignment. At the gradient level, we propose a momentum-driven Exponential Moving Average (MEMA) dynamic scaler. By establishing a robust historical baseline of the optimization trajectory, MEMA actively evaluates instantaneous gradient conflicts and adaptively penalizes harmful distillation signals, guaranteeing stable convergence. Importantly, SPOFA achieves this dual stabilization with an extremely lightweight parameter footprint. Extensive experiments on two mainstream benchmarks demonstrate that SPOFA achieves state-of-the-art accuracy, significantly outperforming computationally expensive methods while introducing only minimal computational overhead compared to standard baselines.

Related papers

• Linear Stability Analysis of an INDI Pitch-Rate Controller under Model Mismatch for a Tilt-Rotor VTOL UAV [0.0]
  Incremental Dynamic Inversion (INDI) is attractive for unmanned aerial vehicle (UAV) flight control because it reduces dependence on a full aerodynamic model.<n>This paper isolates the pitch-rate/elevon subchannel of an existing cascaded INDI controller and studies its linear stability under model mismatch.
  arXiv  Detail & Related papers  (2026-07-17T19:35:46Z)
• Energy-Structured Low-Rank Adaptation for Continual Learning [78.5390284258307]
  We propose textbfEnergy-Concentrated and textbfEnergy-Ordered textbfLow-textbfRank textbfAdaptation (E$2$-LoRA)<n>By explicitly ordering and concentrating knowledge into leading ranks, E$2$-LoRA frees capacity for subsequent tasks.
  arXiv  Detail & Related papers  (2026-05-26T12:55:02Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Taming the Instability: A Robust Second-Order Optimizer for Federated Learning over Non-IID Data [77.19117648492104]
  We present Federated Robust Curvature Optimization (FedRCO), a novel second-order optimization framework designed to improve convergence speed and reduce communication cost.<n>FedRCO addresses these challenges by integrating an efficient approximate curvature with a provable stability mechanism.<n>We show that FedRCO achieves superior robustness against diverse non-IID scenarios while achieving higher accuracy and faster convergence than both state-of-the-art first-order and second-order methods.
  arXiv  Detail & Related papers  (2026-03-30T11:37:46Z)
• Dual-Stage Invariant Continual Learning under Extreme Visual Sparsity [8.16821029459195]
  We show that background-driven gradients destabilize the feature backbone during sequential domain shifts.<n>We propose a dual-stage invariant continual learning framework via joint distillation.<n> Experiments on a high-resolution space-based RSO detection dataset show consistent improvement over established continual object detection methods.
  arXiv  Detail & Related papers  (2026-03-27T09:03:49Z)
• Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives [22.29000001610794]
  Standard negative log-likelihood for Supervised Fine-Tuning (SFT) applies uniform token-level weighting.<n>This rigidity creates a two-fold failure mode: (i) overemphasizing low-probability targets can amplify gradients on noisy supervision and disrupt robust priors, and (ii) uniform weighting provides weak sharpening when the model is already confident.<n>Existing methods fail to resolve the resulting plasticity--stability dilemma, often suppressing necessary learning signals alongside harmful ones.<n>We introduce Dynamic Entropy Fine-Tuning (DEFT), a parameter-free objective that modulates the
  arXiv  Detail & Related papers  (2026-02-11T22:56:43Z)
• Unifying Sign and Magnitude for Optimizing Deep Vision Networks via ThermoLion [0.0]
  Current paradigms impose a static compromise on information channel drift parameters.<n>We introduce a "low-dimensional" exploration model and a "low-dimensional" dynamic alignment framework.
  arXiv  Detail & Related papers  (2025-12-01T17:04:17Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• Beyond the Edge of Stability via Two-step Gradient Updates [49.03389279816152]
  Gradient Descent (GD) is a powerful workhorse of modern machine learning. GD's ability to find local minimisers is only guaranteed for losses with Lipschitz gradients. This work focuses on simple, yet representative, learning problems via analysis of two-step gradient updates.
  arXiv  Detail & Related papers  (2022-06-08T21:32:50Z)

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.