Decoupling Spatio-Temporal Prediction: When Lightweight Large Models Meet Adaptive Hypergraphs

解耦(概率) 计算机科学 人工智能 控制工程 工程类
作者
Jiawen Chen,Qi Shao,Duxin Chen,Wenwu Yu
标识
DOI:10.1145/3711896.3736904
摘要

Spatio-temporal prediction is a pivotal task with broad applications in traffic management, climate monitoring, energy scheduling, etc. However, existing methodologies often struggle to balance model expressiveness and computational efficiency, especially when scaling to large real-world datasets. To tackle these challenges, we propose STH-SepNet (Spatio-Temporal Hypergraph Separation Networks), a novel framework that decouples temporal and spatial modeling to enhance both efficiency and precision. Therein, the temporal dimension is modeled using lightweight large language models, which effectively capture low-rank temporal dynamics. Concurrently, the spatial dimension is addressed through an adaptive hypergraph neural network, which dynamically constructs hyperedges to model intricate, higher-order interactions. A carefully designed gating mechanism is integrated to seamlessly fuse temporal and spatial representations. By leveraging the fundamental principles of low-rank temporal dynamics and spatial interactions, STH-SepNet offers a pragmatic and scalable solution for spatio-temporal prediction in real-world applications. Extensive experiments on large-scale real-world datasets across multiple benchmarks demonstrate the effectiveness of STH-SepNet in boosting predictive performance while maintaining computational efficiency. This work may provide a promising lightweight framework for spatio-temporal prediction, aiming to reduce computational demands and while enhancing predictive performance. Our code is avaliable at https://github.com/SEU-WENJIA/ST-SepNet-Lightweight-LLMs-Meet-Adaptive-Hypergraphs.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
谦让的沛蓝完成签到 ,获得积分10
刚刚
11完成签到,获得积分10
刚刚
Chen完成签到,获得积分10
1秒前
砍柴少年发布了新的文献求助10
1秒前
1秒前
2秒前
3秒前
Danmo发布了新的文献求助10
3秒前
3秒前
美好斓发布了新的文献求助10
3秒前
科研小白完成签到,获得积分10
3秒前
蓝调小丸子完成签到 ,获得积分10
3秒前
白紫莹完成签到,获得积分10
4秒前
菠萝吹雪发布了新的文献求助10
4秒前
5秒前
雯yuki发布了新的文献求助10
6秒前
可靠忆安完成签到,获得积分10
7秒前
虚心飞鸟完成签到,获得积分10
7秒前
Passerby完成签到,获得积分10
7秒前
曲奇饼干发布了新的文献求助20
7秒前
8秒前
NexusExplorer应助pups采纳,获得80
8秒前
9秒前
小李发布了新的文献求助10
9秒前
研友_nPxRRn完成签到,获得积分10
9秒前
9秒前
9秒前
wsy完成签到,获得积分10
9秒前
杜晓倩发布了新的文献求助10
9秒前
10秒前
10秒前
10秒前
10秒前
12秒前
Gauss应助freesia采纳,获得50
12秒前
13秒前
13秒前
13秒前
海人完成签到,获得积分10
14秒前
14秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
HYDROLYSE ACIDE DE QUELQUES DIOXASPIROCYCLANES 1314
Essentials of Carbohydrate Chemistry and Biochemistry, 4th Edition 800
Navigating Normative Orders. Interdisciplinary Perspectives 800
1 Peter and Christ's Descent to the Dead in Its Early Christian Reception 700
Organizational Behavior 510
Management and the Arts 510
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7746549
求助须知:如何正确求助?哪些是违规求助? 9294420
关于积分的说明 20224582
捐赠科研通 7326479
什么是DOI,文献DOI怎么找? 3308115
关于科研通互助平台的介绍 2460125
邀请新用户注册赠送积分活动 2319789