Results 21 to 30 of about 229,000 (311)
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009 As a fundamental problem in pattern recognition, graph matching has applications in a variety of fields, from computer vision to computational biology. In graph matching, patterns are modeled as graphs and pattern recognition amounts to finding a correspondence between the nodes of different graphs.
Tibério S. Caetano +4 more
openaire +4 more sources
Learning Graph Representations [PDF]
, 2021 Social and information networks are gaining huge popularity recently due to their various applications. Knowledge representation through graphs in the form of nodes and edges should preserve as many characteristics of the original data as possible.
Rucha Bhalchandra Joshi +1 more
openaire +2 more sources
Contrastive and attentive graph learning for multi-view clustering [PDF]
, 2022 Graph-based multi-view clustering aims to take advantage of multiple view graph information to provide clustering solutions. The consistency constraint of multiple views is the key of multi-view graph clustering.
Li, Lin +4 more
core +1 more source
Learning Graph Representations With Maximal Cliques. [PDF]
, 2021 Non-Euclidean property of graph structures has faced interesting challenges when deep learning methods are applied. Graph convolutional networks (GCNs) can be regarded as one of the successful approaches to classification tasks on graph data, although ...
Zare, H +9 more
core +2 more sources
Learning graph normalization for graph neural networks [PDF]
Neurocomputing, 2022 15 pages, 3 figures, 6 ...
Yihao Chen +4 more
openaire +2 more sources
Graph Transformer for Graph-to-Sequence Learning
Proceedings of the AAAI Conference on Artificial Intelligence, 2020 The dominant graph-to-sequence transduction models employ graph neural networks for graph representation learning, where the structural information is reflected by the receptive field of neurons. Unlike graph neural networks that restrict the information exchange between immediate neighborhood, we propose a new model, known as Graph Transformer, that ...
Deng Cai 0002, Wai Lam
openaire +3 more sources
Multimodal learning with graphs
Nature Machine Intelligence, 2023 Artificial intelligence for graphs has achieved remarkable success in modeling complex systems, ranging from dynamic networks in biology to interacting particle systems in physics. However, the increasingly heterogeneous graph datasets call for multimodal methods that can combine different inductive biases: the set of assumptions that algorithms use to
Yasha Ektefaie +4 more
openaire +3 more sources
Learning Graphs to Match [PDF]
2013 IEEE International Conference on Computer Vision, 2013 Many tasks in computer vision are formulated as graph matching problems. Despite the NP-hard nature of the problem, fast and accurate approximations have led to significant progress in a wide range of applications. Learning graph models from observed data, however, still remains a challenging issue.
Cho, Minsu +2 more
openaire +2 more sources
Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming [PDF]
, 2022 Graph representation learning (GRL) is critical for graph-structured data analysis. However, most of the existing graph neural networks (GNNs) heavily rely on labeling information, which is normally expensive to obtain in the real world.
Li, Ming +13 more
core +2 more sources
Preventing Failures by Dataset Shift Detection in Safety-Critical Graph Applications
Frontiers in Artificial Intelligence, 2021 Dataset shift refers to the problem where the input data distribution may change over time (e.g., between training and test stages). Since this can be a critical bottleneck in several safety-critical applications such as healthcare, drug-discovery, etc.,
Hoseung Song +2 more
doaj +1 more source