This paper proposes a spatiotemporal hypergraph-driven framework integrating high-order topological feature extraction with dynamic resource modeling, and introduces dynamic hypergraph sequences to naturally encompass local conflict domains, mitigating the topological blind spots and “over-smoothing” issues inherent in traditional pairwise graphs.
Abstract
Cloud-edge collaborative inference, particularly the synergy between edge-deployed small models and cloud-based large models, demonstrates extensive application value in meeting the high-accuracy and low-latency demands of emerging artificial intelligence. However, existing dynamic offloading methods exhibit limitations in modeling the “many-to-many” high-order resource competition that arises when numerous small models concurrently access shared large model interfaces. They lack a unified representation capable of adapting to time-varying network congestion and often ignore the spatial exclusivity of concurrent tasks when sharing bandwidth and large model interfaces. To overcome these limitations, this paper proposes a spatiotemporal hypergraph-driven framework integrating high-order topological feature extraction with dynamic resource modeling. This framework introduces dynamic hypergraph sequences to naturally encompass local conflict domains, mitigating the topological blind spots and “over-smoothing” issues inherent in traditional pairwise graphs. In the first stage, a spatiotemporal hypergraph neural network (ST-HGNN) encodes complex spatial dependencies and predicts temporal resource bottlenecks. Subsequently, a weighted multi-dimensional hypergraph matching (WTHM) strategy transforms the NP-hard mixed-integer nonlinear programming problem into an efficient heuristic search. Trace-driven simulation results based on real-world urban trajectories (EUA and T-Drive) demonstrate that the proposed framework achieves a robust normalized VCI score of 0.64 even during extreme congestion peaks. By consistently achieving an absolute VCI improvement of 0.17 to 0.38 over traditional bipartite-graph and proximity-based baselines, the framework significantly mitigates cascading queuing failures. Moreover, the developed dual-timescale asynchronous architecture strictly confines online execution to the millisecond scale, validating its capability to balance inference accuracy and latency across dynamic cloud-edge environments.
A unified technical roadmap highlighting four main open challenges: i.e., serverless cold-start bottlenecks, mobility in LEO satellite deployments, lack of multi-vendor validation in empirical studies, and security weaknesses in zero-trust architectures is summarized.
Maqsood Ul Haq, Nor Asilah Wati Abdul Hamid, Shamala K. Subramaniam et al.· International Journal on Adv...· 0 citations
A Multi-State Semantic Cache (MSSC) framework that dynamically maps knowledge chunks into three mutually exclusive states: zero cache, index cache, and full cache is proposed that reduces average service latency by over 40% in dynamic scenarios and suppresses backhaul reconfiguration traffic by up to 38% compared to co...
Kang Liu, Guang-Ping Xu, Ya-Ru Fu et al.· Proceedings of the Internati...· 0 citations
DABO is proposed, a calibration-aware binary offloading method for collaborative large–small model inference that maintains competitive end-to-end accuracy while processing an average of 83.72% of requests at the edge.
Chen Zhu, Yi-Ming Su, Chenwenjie Mao et al.· IEEE Access· 0 citations
Pretrained Foundation Models (PFMs) enable highaccuracy inference services but are typically deployed in remote datacenters, resulting in prohibitively high inference delay. Mobile Edge Computing (MEC) can mitigate such high delays by caching PFMs or their fine-tuned variants on cloudlets located close to end users. Ho...
Li-Zhe Zhou, Qiu-Fen Xia, Zi-Chuan Xu et al.· IEEE Transactions on Paralle...· 0 citations
As Metaverse scenarios grow increasingly complex, users place higher demands on real-time rendering and interactive experiences for static and dynamic resources. Existing research largely focuses on static scene transmission, which is inadequate for joint rendering with dynamic Non-Player Characters (NPC). Moreover, ce...
Sheng-Lu Zhao, Zheng Wan, Yan-Ping Yu et al.· IEEE Transactions on Mobile...· 0 citations
An online priority-driven filter-and-expand framework with several effective pruning techniques and a powerful geometric slope optimization for rapid temporal wedge conductance calculation is developed and a novel temporal wedge conductance metric is proposed that explicitly balances internal density and external spars...
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduJul 15, 2026
Assistant Professor Pat Pataranutaporn describes a new interface that lets everyday users glimpse inside an AI's neural network before their chatbot ever says a word.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.