ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization

• URL: http://arxiv.org/abs/2511.10971v1
• Date: Fri, 14 Nov 2025 05:31:37 GMT
• Title: ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization
• Authors: Anzhe Cheng, Shukai Duan, Shixuan Li, Chenzhong Yin, Mingxi Cheng, Heng Ping, Tamoghna Chattopadhyay, Sophia I Thomopoulos, Shahin Nazarian, Paul Thompson, Paul Bogdan,
• Abstract summary: ERMoE is a sparse MoE transformer that replaces learned gating logits with an "Eigenbasis Score"<n>We show that ERMoE achieves state-of-the-art accuracy on ImageNet classification and cross-modal image-text retrieval benchmarks.<n>A 3D MRI variant (ERMoE-ba) improves brain age prediction accuracy by more than 7% and yields interpretable expert specializations.
• Score: 13.182475975397251
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mixture-of-Experts (MoE) architectures expand model capacity by sparsely activating experts but face two core challenges: misalignment between router logits and each expert's internal structure leads to unstable routing and expert underutilization, and load imbalances create straggler bottlenecks. Standard solutions, such as auxiliary load-balancing losses, can reduce load disparities but often weaken expert specialization and hurt downstream performance. To address these issues, we propose ERMoE, a sparse MoE transformer that reparameterizes each expert in a learned orthonormal eigenbasis and replaces learned gating logits with an "Eigenbasis Score", defined as the cosine similarity between input features and an expert's basis. This content-aware routing ties token assignments directly to experts' representation spaces, stabilizing utilization and promoting interpretable specialization without sacrificing sparsity. Crucially, ERMoE removes the need for explicit balancing losses and avoids the interfering gradients they introduce. We show that ERMoE achieves state-of-the-art accuracy on ImageNet classification and cross-modal image-text retrieval benchmarks (e.g., COCO, Flickr30K), while naturally producing flatter expert load distributions. Moreover, a 3D MRI variant (ERMoE-ba) improves brain age prediction accuracy by more than 7\% and yields anatomically interpretable expert specializations. ERMoE thus introduces a new architectural principle for sparse expert models that directly addresses routing instabilities and enables improved performance with scalable, interpretable specialization.

Related papers

• A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs [64.8510381475827]
  Sparse Mixture-of-Experts (SMoE) architectures are increasingly used to scale large language models efficiently.<n>SMoE models often suffer from severe load imbalance across experts, where a small subset of experts receives most tokens while others are underutilized.<n>We present a systematic analysis of expert routing during inference and identify three findings: (i) load imbalance persists and worsens with larger batch sizes, (ii) selection frequency does not reliably reflect expert importance, and (iii) overall expert workload and importance can be estimated using a small calibration set.
  arXiv  Detail & Related papers  (2026-02-23T15:11:16Z)
• Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization [10.669680236190432]
  We propose two plug-and-play regularization losses that enhance MoE specialization and routing efficiency.<n>We implement both losses as a drop-in Megatron-LM module.
  arXiv  Detail & Related papers  (2026-02-15T14:19:12Z)
• SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning [83.66308307152808]
  We propose StAbilized Mixture-of-Experts (SAME) for Multimodal Continual Instruction Tuning (MCIT)<n>SAME stabilizes expert selection by decomposing routing dynamics into subspaces and updating only task-relevant directions.<n>It also introduces adaptive expert activation to freeze selected experts during training, reducing redundant and cross-task interference.
  arXiv  Detail & Related papers  (2026-02-02T11:47:06Z)
• EMoE: Eigenbasis-Guided Routing for Mixture-of-Experts [13.726411744252509]
  Eigen-Mixture-of-Experts (EMoE) is a novel architecture that leverages a routing mechanism based on a learned orthonormal specialization eigenbasis.<n>EMoE projects input tokens onto this shared eigenbasis and routes them based on their alignment with the principal components of the feature space.<n>This principled, geometric partitioning of data intrinsically promotes both balanced expert utilization and the development of diverse, specialized experts.
  arXiv  Detail & Related papers  (2026-01-17T18:49:25Z)
• Spectral Manifold Regularization for Stable and Modular Routing in Deep MoE Architectures [2.538209532048867]
  Mixture of Experts (MoE) architectures enable efficient scaling of neural networks but suffer from expert collapse.<n>We propose the Spectrally-Regularized Mixture of Experts (SR-MoE), which imposes geometric constraints on the routing manifold to enforce structural modularity.
  arXiv  Detail & Related papers  (2026-01-07T12:59:37Z)
• Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution [76.66229730098759]
  In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models.<n>We propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution.<n>We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert.
  arXiv  Detail & Related papers  (2025-11-20T04:11:44Z)
• Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder [59.89996751196727]
  Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models.<n>SAEs' hidden layers have high dimensionality to satisfy sparsity constraints, resulting in prohibitive training and inference costs.<n>Recent Mixture of Experts (MoE) approaches attempt to address this by SAEs into narrower expert networks with gated activation.<n>We propose two key innovations: (1) Multiple Expert Activation that simultaneously engages semantically weighted expert subsets to encourage specialization, and (2) Feature Scaling that enhances diversity through adaptive high-frequency scaling.
  arXiv  Detail & Related papers  (2025-11-07T22:19:34Z)
• Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs [54.95810313530111]
  DERN is a task-agnostic and retraining-free framework for expert pruning and reconstruction.<n>It improves performance by more than 5% on commonsense reasoning and MMLU benchmarks under 50% expert sparsity.
  arXiv  Detail & Related papers  (2025-09-12T16:09:39Z)
• Load Balancing Mixture of Experts with Similarity Preserving Routers [30.279616888339543]
  Sparse Mixture of Experts (MoE) models offer a scalable and efficient architecture for training large neural networks.<n>We introduce a novel load balancing loss that preserves token-wise relational structure.<n>Our results show that applying our loss to the router results in 36% faster convergence and lower redundancy.
  arXiv  Detail & Related papers  (2025-06-16T22:22:59Z)
• Advancing Expert Specialization for Better MoE [22.88847592702946]
  Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input.<n>We observe that the commonly used auxiliary load balancing loss often leads to expert overlap and overly uniform routing.<n>We propose a simple yet effective solution that introduces two complementary objectives.
  arXiv  Detail & Related papers  (2025-05-28T13:09:47Z)
• HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference [54.40808356999408]
  We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency. HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.
  arXiv  Detail & Related papers  (2024-11-03T04:25:46Z)
• Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization [51.98792406392873]
  Mixture of Experts (MoE) provides a powerful way to decompose dense layers into smaller, modular computations. A major challenge lies in the computational cost of scaling the number of experts high enough to achieve fine-grained specialization. We propose the Multilinear Mixture of Experts ($mu$MoE) layer to address this, focusing on vision models.
  arXiv  Detail & Related papers  (2024-02-19T21:20:22Z)
• MoEC: Mixture of Expert Clusters [93.63738535295866]
  Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make experts conditionally activated. However, as the number of experts grows, MoE with outrageous parameters suffers from overfitting and sparse data allocation.
  arXiv  Detail & Related papers  (2022-07-19T06:09:55Z)

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.