The implications of the proposed TAGNN framework on such applications as anomaly detection, social media analytics, and traffic forecasting are that the proposed framework provides an end-to-end solution that promotes accuracy, efficiency, and temporal consistency in dynamic graph learning.
Wassan Hayale, R. S. Ali, Raghda Abd Ul Rab Abd Ul Hasan et al.· Mesopotamian Journal of Big...· 0 citations
Hierarchical Interpolating MeshGraphNets (HI-MGN), a multiscale extension of MeshGraphNets for efficient long-range communication on unstructured meshes that replaces the flat processor with a hierarchical multiscale processor that coarsens graphs using farthest-point sampling and Voronoi partitioning while preserving the original mesh topology.
SiHun Lee, D. Park, Taesoo Bang et al.· 0 citations
A method combining graph neural networks (GNNs) to construct a propagation path modeling framework that integrates topological structure and node status time series characteristics and is directly applicable to reliability analysis of electromagnetic communication links in power networks.
L.-N. Hu, Y. Tang, L. Ye· Advanced Electromagnetics· 0 citations
Two structural ablations indicate that both the sparse connectivity and the estimated grouping of characteristics contribute to the ranking advantage, and both effects remain significant after correcting for multiple testing.
Hongyu Lin, Yulin Chen, Yuanrong Wang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Investigation of when and why critical-class-first scheduling is effective in CITO and a GNN-D3QN joint framework is proposed to unify critical class identification and test order optimization suggests that the effectiveness of critical-class prioritization is structurally conditioned by the topological roles and distribution patterns of critical classes.
Jia-Yi Wang, Fan Chen, Miao Zhang et al.· Journal of King Saud Univers...· 0 citations
A Self-Supervised Graph Vision Transformer Network (SS-GVTNet) in detecting and classifying pulmonary nodules and malignancies through CT scanning and offers credible classification of malignancy, which help clinicians in early diagnosis and treatment planning is suggested.
Koventhan G. M., R. Ramkumar· Adolescência e Saúde· 0 citations
An intelligent employment decision support system that integrates multi-source heterogeneous data with GNNs (Graph Neural Networks), which can effectively identify structurally mismatched groups, provide quantitative basis for professional adjustment and regional talent policies, and demonstrate good technical performance and institutional embedding potential is constructed.
Wenbo Jing, Jianhua Zhao· International Conference on...· 0 citations
Although the framework performed slightly better than the best baseline under the tested conditions, the improvement was not statistically significant enough to establish consistent superiority and emphasize the need for further evaluation of deployment time, base-rate estimation, and real-world cybersecurity scenarios.
N. Deotale, Annaluri Sreenivasa Rao, E. Sreedevi et al.· International Journal for Gl...· 0 citations
Overall, the proposed AI–DFT framework provides a physically interpretable computational approach for climate-aware prioritization of perovskite photovoltaic materials by connecting quantum-derived descriptors, ML predictions, environmental factors, sensitivity-based robustness assessment, and device-level performance estimation.
Douglas Yeboah, Claudia Asare, Prince Gaka· Engineering Research Express· 0 citations
This work observes that predictive uncertainty decreases as latent representations shift toward lower-variance posterior directions, even though the posterior variance does not contract, and proposes Alignment-Guided Learning (AGL), which explicitly promotes this alignment during training.
S. Choi, Damdae Park, Junhyuk Choi et al.· 0 citations
Antenna selection is investigated as a means of reducing radio-frequency (RF) chain power in massive multiple-input multiple-output (MIMO) base stations under realistic channel state information (CSI) impairments. The study is motivated by the mismatch between conventional selection objectives and multi-cell operation with estimation error, pilot contamination, spatial correlation and inter-cell interference. APCS-Boost-R is introduced as the primary contribution. An interference-whitened D-optimal seed is combined with projected rank-one exchanges and a calibrated surrogate that incorporates a user-side interference-plus-noise report and a closed-form estimation-error correction. APCS-Boost-RG is retained as an optional graph neural network (GNN) refinement in which residual exchanges are ranked after the algebraic solution has been formed, while feasibility and non-degradation of the calibrated surrogate are verified deterministically. In a three-cell urban macro configuration derived from Third Generation Partnership Project (3GPP) TR 38.901 with 64 antennas, 16 active RF chains and eight users per cell, APCS-Boost-R achieves 19.364 bit/s/Hz over 200 paired realizations. Improvements of 2.58 percent over APCS-Boost, 6.76 percent over greedy search and 10.16 percent over a genetic algorithm are obtained. APCS-Boost-RG adds 0.019 bit/s/Hz but is treated as an optional refinement because it requires a second-stage neighborhood evaluation and offline model maintenance. In the archived common timing record, APCS-Boost-R requires 20.376 ms per three-cell realization, compared with 12.728 ms for APCS-Boost, 57.775 ms for norm-initialized greedy search and 41.302 ms for the genetic algorithm, while APCS-Boost-RG requires 24.0 ms versus 20.4 ms for APCS-Boost-R in the separate archived learned-stage record. Separate reconstructions on the documented reproducibility host require 55.3±14.5 ms for APCS-Boost-R and 592.2±181.9 ms for a complete APCS-Boost-RG rebuild. Additional paired examinations confirm robustness across stronger search budgets, report imperfections, regularized precoding, coordination, near-field sensitivity, hardware perturbations, and configurations ranging from 32 to 128 antennas and one to seven cells.
Iacovos I. Ioannou, V. Vassiliou· Network· 0 citations
ReCoG (Reciprocal Co-Evolution for Multimodal Graph Learning) is proposed, a new learning paradigm that tightly couples graph structure learning and multimodal representation learning through end-to-end reciprocal interaction and yields greater expressiveness than decoupled or two-stage formulations.
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.
MIT News · Artificial Intelligence· news.mit.eduJul 6, 2026
PhD student Rachel Sava, winner of the Envisioning the Future of Computing Prize, explores transformative improvements and dystopian risks of neural technology.
