Edge-aware Decoding for Neural Asymmetric Routing

2026-06-01 · Li Liang, Jinbiao Chen, Zizhen Zhang arxiv

Neural asymmetric routing models increasingly encode directionality through matrix representations and asymmetry-aware attention. The final routing action, however, is not a node in isolation but a directed transition chosen under the current partial route. This creates a representation--decision mismatch: pairwise cost information may be encoded upstream while the final candidate logit is still largely parameterized as context--node compatibility. We propose a decoder-design principle for neural asymmetric routing: the final score should explicitly expose transition-level quantities suggested by the problem's cost-to-go structure. We instantiate this principle with an edge-aware decoder that adds candidate-specific terms for the current directed edge, return-to-start closure, and static lightweight lookahead, while keeping the representation backbone fixed. On a controlled SVD/Sinkhorn asymmetric backbone, the decoder improves over the RADAR reference when trained on ATSP-100 and evaluated zero-shot on ATSP-100/200/500/1000, reducing the ATSP-1000 gap from $4.13\%$ to $2.73\%$. On ACVRP, the same score-level modification shows the same qualitative trend under a richer routing state. ATSP ablations and directed-transition diagnostics sharpen the mechanism: the strongest evidence concerns sensitivity to the current directed edge, while closure and static lookahead act as heuristic continuation cues. The results support a mechanism study: a key decoder-side signal in neural asymmetric routing is decision-time exposure of transition-level edge information.

📄 PDF Abstract BibTeX arXiv:2606.02136

Code (0)

등록된 구현이 없습니다.

SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver

2026-05-23 · Rongsheng Chen, Changliang Zhou, Canhong Yu, Yuanyao Chen 외 arxiv

Generalist neural routing solvers have shown great potential in solving diverse vehicle routing problems (VRPs) with a unified model. However, existing solvers are typically limited to symmetric settings or degrade in pe…

Zero-shot Generalization

S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices

2026-08-15 · Haochen Huang, Shengxuan Qiu, Meng Li arxiv

Deploying large language models (LLMs) for inference on edge devices is challenging due to severe memory and bandwidth constraints. While speculative decoding and Mixture-of-Experts (MoE) have been proposed to improve in…

From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing

2026-06-05 · Guannan Lai, Haoran Hu, Long Chen, Zhenguo Li 외 arxiv

Existing LLM routing methods often construct supervision from a single sampled response for each query--model pair. Because LLM generation is stochastic, however, such an observation can be an unstable estimate of model …

Stable Routing for Mixture-of-Experts in Class-Incremental Learning

2026-05-17 · Zirui Guo, Quan Cheng, Da-Wei Zhou, Lijun Zhang arxiv

Class-incremental learning (CIL) requires models to learn new classes sequentially while preserving prior knowledge. Recently, approaches that combine pre-trained models with mixture-of-experts (MoE) have received increa…

class-incremental learning

Anomaly-Aware Vision-Language Adapters for Zero-Shot Anomaly Detection

2026-05-12 · Muhammad Aqeel, Maham Nazir, Uzair Khan, Marco Cristani 외 arxiv

Zero-shot anomaly detection aims to identify defects in unseen categories without target-specific training. Existing methods usually apply the same feature transformation to all samples, treating normal and anomalous dat…

Domain Generalization Anomaly Detection