paper-with-me

홈 › Papers

ViTE: Virtual Graph Trajectory Expert Router for Pedestrian Trajectory Prediction

2025-11-15 · Ruochen Li, Zhanxing Zhu, Tanqiu Qiao, Hubert P. H. Shum arxiv

Pedestrian trajectory prediction is critical for ensuring safety in autonomous driving, surveillance systems, and urban planning applications. While early approaches primarily focus on one-hop pairwise relationships, recent studies attempt to capture high-order interactions by stacking multiple Graph Neural Network (GNN) layers. However, these approaches face a fundamental trade-off: insufficient layers may lead to under-reaching problems that limit the model's receptive field, while excessive depth can result in prohibitive computational costs. We argue that an effective model should be capable of adaptively modeling both explicit one-hop interactions and implicit high-order dependencies, rather than relying solely on architectural depth. To this end, we propose ViTE (Virtual graph Trajectory Expert router), a novel framework for pedestrian trajectory prediction. ViTE consists of two key modules: a Virtual Graph that introduces dynamic virtual nodes to model long-range and high-order interactions without deep GNN stacks, and an Expert Router that adaptively selects interaction experts based on social context using a Mixture-of-Experts design. This combination enables flexible and scalable reasoning across varying interaction patterns. Experiments on three benchmarks (ETH/UCY, NBA, and SDD) demonstrate that our method consistently achieves state-of-the-art performance, validating both its effectiveness and practical efficiency.

📄 PDF Abstract BibTeX arXiv:2511.12214

Code (0)

등록된 구현이 없습니다.

Tasks

Trajectory PredictionGraph Neural NetworkAutonomous Driving

Similar Papers 제목 키워드 기반

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

2026-03-05 · Yilong Chen, Naibin Gu, Junyuan Shang, Zhenyu Zhang 외 arxiv

Mixture-of-Experts (MoE) decouples model capacity from per-token computation, yet their scalability remains limited by the physical dimensions of depth and width. To overcome this, we propose Mixture of Universal Experts…

When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models

2026-05-08 · Youngsik Yoon, Siwei Wang, Wei Chen, Jungseul Ok arxiv

Mixture-of-Experts (MoE) language models route each token to a small subset of experts, but whether the routes selected by a trained top-$k$ router are good ones is rarely evaluated directly. Holding the model fixed, we …

Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection

2026-02-22 · Hossein Shokouhinejad, Roozbeh Razavi-Far, Griffin Higgins, Ali. A Ghorbani arxiv

Mixture-of-Experts (MoE) offers flexible graph reasoning by combining multiple views of a graph through a learned router. We investigate routing-aware explanations for MoE graph models in malware detection using control …

Malware Detection

PathRouter: Aligning Rewards with Retrieval Quality in Agentic Graph Retrieval-Augmented Generation

2026-06-15 · Bo Wang, Heyan Huang, Yaolin Li, Wei Tang 외 arxiv

Agentic GraphRAG trains language-model agents to iteratively retrieve and reason over graph-structured evidence, enabling more accurate and context-aware decision-making by efficiently navigating complex information netw…

Reinforcement Learning

PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning

2026-05-29 · Daize Dong, Junlin Chen, Haolong Jia, Jiang Liu 외 arxiv

Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs often suffers from training instability. A root cause is router drift, i.e…

Reinforcement Learning