Zobrazeno 1 - 10
of 106
pro vyhledávání: '"Ma, Xueqi"'
We present a new approach for generating 3D house wireframes with semantic enrichment using an autoregressive model. Unlike conventional generative models that independently process vertices, edges, and faces, our approach employs a unified wire-base
Externí odkaz:
http://arxiv.org/abs/2407.12267
Graph contrastive learning (GCL) is a popular method for leaning graph representations by maximizing the consistency of features across augmented views. Traditional GCL methods utilize single-perspective i.e. data or model-perspective) augmentation t
Externí odkaz:
http://arxiv.org/abs/2406.00403
Autor:
Liu, Chuang, Yao, Zelin, Zhan, Yibing, Ma, Xueqi, Tao, Dapeng, Wu, Jia, Hu, Wenbin, Pan, Shirui, Du, Bo
Graph Masked Autoencoders (GMAEs) have emerged as a notable self-supervised learning approach for graph-structured data. Existing GMAE models primarily focus on reconstructing node-level information, categorizing them as single-scale GMAEs. This meth
Externí odkaz:
http://arxiv.org/abs/2405.10642
Graph masked autoencoders (GMAE) have emerged as a significant advancement in self-supervised pre-training for graph-structured data. Previous GMAE models primarily utilize a straightforward random masking strategy for nodes or edges during training.
Externí odkaz:
http://arxiv.org/abs/2404.15806
Graph Transformers (GTs) have demonstrated their advantages across a wide range of tasks. However, the self-attention mechanism in GTs overlooks the graph's inductive biases, particularly biases related to structure, which are crucial for the graph t
Externí odkaz:
http://arxiv.org/abs/2404.15729
Graph Transformers (GTs) have achieved impressive results on various graph-related tasks. However, the huge computational cost of GTs hinders their deployment and application, especially in resource-constrained environments. Therefore, in this paper,
Externí odkaz:
http://arxiv.org/abs/2312.05479
Graph pooling has been increasingly recognized as crucial for Graph Neural Networks (GNNs) to facilitate hierarchical graph representation learning. Existing graph pooling methods commonly consist of two stages: selecting top-ranked nodes and discard
Externí odkaz:
http://arxiv.org/abs/2311.12644
Autor:
Liu, Chuang, Ma, Xueqi, Zhan, Yibing, Ding, Liang, Tao, Dapeng, Du, Bo, Hu, Wenbin, Mandic, Danilo
Graph Neural Networks (GNNs) tend to suffer from high computation costs due to the exponentially increasing scale of graph data and the number of model parameters, which restricts their utility in practical applications. To this end, some recent work
Externí odkaz:
http://arxiv.org/abs/2207.08629
Autor:
Liu, Qing, Li, Xiangyu, Tang, Qinglong, Liu, Xuecun, Wang, Yongfang, Song, Mingshuai, Chen, Xiaoxiao, Pozzolina, Marina, Höfer, Juan, Ma, Xueqi, Xiao, Liang
Publikováno v:
In Ecotoxicology and Environmental Safety 15 October 2024 285
Publikováno v:
In Neural Networks January 2025 181