Results 81 to 90 of about 2,491 (218)

Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation

, 2021
Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems. Most existing social recommendation models exploit pairwise relations to mine potential user preferences.
Zhang, Xiangliang, Junliang Yu, Li, Jundong, Hongzhi Yin, Jundong Li, Nguyen Quoc Viet Hung, Hung, Nguyen Quoc Viet, Wang, Qinyong, Qinyong Wang, Yu, Junliang, Nguyen, Quoc Viet Hung, Yin, Hongzhi, Xiangliang Zhang   +12 more
core   +1 more source

Learning Hypergraph-regularized Attribute Predictors [PDF]

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
This is an attribute learning paper accepted by CVPR ...
Sheng Huang 0001, Mohamed Elhoseiny, Ahmed M. Elgammal, Dan Yang 0001   +3 more
openaire   +2 more sources

Zarankiewicz bounds from distal regularity lemma

Bulletin of the London Mathematical Society, Volume 58, Issue 3, March 2026.
Abstract Since Kővári, Sós and Turán proved upper bounds for the Zarankiewicz problem in 1954, much work has been undertaken to improve these bounds, and some have done so by restricting to particular classes of graphs. In 2017, Fox, Pach, Sheffer, Suk and Zahl proved better bounds for semialgebraic binary relations, and this work was extended by Do in
Mervyn Tong
wiley   +1 more source

Un-normlized and Random Walk Hypergraph Laplacian Un-supervised Learning

, 2015
. Most network-based clustering methods are based on the assumption that the labels of two adjacent vertices in the network are likely to be the same. However, assuming the pairwise relationship between vertices is not complete.
Hoang Trang, Loc Hoang Tran, Linh Hoang Tran   +2 more
core   +1 more source

Small triangles

Journal of the London Mathematical Society, Volume 113, Issue 3, March 2026.
Abstract Heilbronn's triangle problem is a classical question in discrete geometry. It asks to determine the smallest number Δ=Δ(N)$\Delta = \Delta (N)$ for which every collection in N$N$ points in the unit square spans a triangle with area at most Δ$\Delta$.
Dmitrii Zakharov
wiley   +1 more source

$$\text {H}^2\text {CAN}$$ H 2 CAN : heterogeneous hypergraph attention network with counterfactual learning for multimodal sentiment analysis

Complex & Intelligent Systems
Multimodal sentiment analysis (MSA) has garnered significant attention for its immense potential in human-computer interaction. While cross-modality attention mechanisms are widely used in MSA to capture inter-modality interactions, existing methods are ...
Changqin Huang, Zhenheng Lin, Qionghao Huang, Xiaodi Huang, Fan Jiang, Jili Chen   +5 more
doaj   +1 more source

Protein Complex Identification Algorithm Based on Hypergraph Network Embedding [PDF]

Jisuanji kexue
Protein complexes are crucial for understanding cellular functions and identifying biological processes,playing critical roles in cell biology.The use of network clustering in PPI networks to identify protein complexes has become a hot research topic in ...
WANG Jie, YANG Xiancan, ZHAO Xingwang
doaj   +1 more source

Semi-supervised Hypergraph Node Classification on Hypergraph Line Expansion

, 2023
Previous hypergraph expansions are solely carried out on either vertex level or hyperedge level, thereby missing the symmetric nature of data co-occurrence, and resulting in information loss.
Yao, Shuochao, Yang, Chaoqi, Wang, Ruijie, Abdelzaher, Tarek   +3 more
core  

Stall‐Free Asynchronous State Repartitioning With a Proactive Workload Tracking Window

Concurrency and Computation: Practice and Experience, Volume 38, Issue 3, February 2026.
ABSTRACT High‐throughput stateful applications rely on dynamic data repartitioning to adapt to changing workloads, but this process presents significant challenges. This paper provides a detailed analysis of such challenges, drilling down into the tradeoffs between adaptation, computational overhead, and service availability. We identify that a primary
Douglas Pereira Luiz, Odorico Machado Mendizabal   +1 more
wiley   +1 more source

Investigating Hypernode Classification of Complex Systems Based on High-order Graph Neural Networks

Guidance, Navigation and Control
Investigating latent interactions beyond direct connections is essential for analyzing complex networks. However, traditional graph structures often fail to capture complex relationships, especially in the high-order interactions among multiple ...
Jiawen Chen, Yanyan He, Duxin Chen, Wenwu Yu   +3 more
doaj   +1 more source