FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385562584> ?p ?o ?g. }

• W4385562584 abstract "Out-of-distribution (OOD) detection, which aims to identify OOD samples from in-distribution (ID) ones in test time, has become an essential problem in machine learning. However, existing works are mostly conducted on Euclidean data, and the problem in graph-structured data remains under-explored. Several recent works begin to study graph OOD detection, but they all need to train a graph neural network (GNN) from scratch with high computational cost. In this work, we make the first attempt to endow a well-trained GNN with the OOD detection ability without modifying its parameters. To this end, we design a post-hoc framework with Adaptive Amplifier for Graph OOD Detection, named AAGOD, concentrating on data-centric manipulation. The insight of AAGOD is to superimpose a parameterized amplifier matrix on the adjacency matrix of each original input graph. The amplifier can be seen as prompts and is expected to emphasize the key patterns helpful for graph OOD detection, thereby enlarging the gap between OOD and ID graphs. Then well-trained GNNs can be reused to encode the amplified graphs into vector representations, and pre-defined scoring functions can further convert the representations into detection scores. Specifically, we design a Learnable Amplifier Generator (LAG) to customize amplifiers for different graphs, and propose a Regularized Learning Strategy (RLS) to train parameters with no OOD data required. Experiment results show that AAGOD can be applied on various GNNs to enable the OOD detection ability. Compared with the state-of-the-art baseline in graph OOD detection, on average AAGOD has 6.21% relative enhancement in AUC and a 34 times faster training speed. Code and data are available at https://github.com/BUPT-GAMMA/AAGOD." @default.
• W4385562584 created "2023-08-04" @default.
• W4385562584 creator A5005922629 @default.
• W4385562584 creator A5051713264 @default.
• W4385562584 creator A5051805730 @default.
• W4385562584 creator A5060417049 @default.
• W4385562584 creator A5075125161 @default.
• W4385562584 creator A5091451498 @default.
• W4385562584 date "2023-08-04" @default.
• W4385562584 modified "2023-09-27" @default.
• W4385562584 title "A Data-centric Framework to Endow Graph Neural Networks with Out-Of-Distribution Detection Ability" @default.
• W4385562584 cites W1976526581 @default.
• W4385562584 cites W2008857988 @default.
• W4385562584 cites W2092114106 @default.
• W4385562584 cites W2099438806 @default.
• W4385562584 cites W2129893339 @default.
• W4385562584 cites W2144182447 @default.
• W4385562584 cites W2566079294 @default.
• W4385562584 cites W3013557831 @default.
• W4385562584 cites W3034213836 @default.
• W4385562584 cites W3133518153 @default.
• W4385562584 cites W4221095033 @default.
• W4385562584 cites W4367046771 @default.
• W4385562584 doi "https://doi.org/10.1145/3580305.3599244" @default.
• W4385562584 hasPublicationYear "2023" @default.
• W4385562584 type Work @default.
• W4385562584 citedByCount "0" @default.
• W4385562584 crossrefType "proceedings-article" @default.
• W4385562584 hasAuthorship W4385562584A5005922629 @default.
• W4385562584 hasAuthorship W4385562584A5051713264 @default.
• W4385562584 hasAuthorship W4385562584A5051805730 @default.
• W4385562584 hasAuthorship W4385562584A5060417049 @default.
• W4385562584 hasAuthorship W4385562584A5075125161 @default.
• W4385562584 hasAuthorship W4385562584A5091451498 @default.
• W4385562584 hasBestOaLocation W43855625841 @default.
• W4385562584 hasConcept C104317684 @default.
• W4385562584 hasConcept C119857082 @default.
• W4385562584 hasConcept C124101348 @default.
• W4385562584 hasConcept C132525143 @default.
• W4385562584 hasConcept C154945302 @default.
• W4385562584 hasConcept C180356752 @default.
• W4385562584 hasConcept C185592680 @default.
• W4385562584 hasConcept C41008148 @default.
• W4385562584 hasConcept C55493867 @default.
• W4385562584 hasConcept C66746571 @default.
• W4385562584 hasConcept C80444323 @default.
• W4385562584 hasConceptScore W4385562584C104317684 @default.
• W4385562584 hasConceptScore W4385562584C119857082 @default.
• W4385562584 hasConceptScore W4385562584C124101348 @default.
• W4385562584 hasConceptScore W4385562584C132525143 @default.
• W4385562584 hasConceptScore W4385562584C154945302 @default.
• W4385562584 hasConceptScore W4385562584C180356752 @default.
• W4385562584 hasConceptScore W4385562584C185592680 @default.
• W4385562584 hasConceptScore W4385562584C41008148 @default.
• W4385562584 hasConceptScore W4385562584C55493867 @default.
• W4385562584 hasConceptScore W4385562584C66746571 @default.
• W4385562584 hasConceptScore W4385562584C80444323 @default.
• W4385562584 hasLocation W43855625841 @default.
• W4385562584 hasOpenAccess W4385562584 @default.
• W4385562584 hasPrimaryLocation W43855625841 @default.
• W4385562584 hasRelatedWork W2971815656 @default.
• W4385562584 hasRelatedWork W2989955213 @default.
• W4385562584 hasRelatedWork W3022222974 @default.
• W4385562584 hasRelatedWork W3033495140 @default.
• W4385562584 hasRelatedWork W3086430417 @default.
• W4385562584 hasRelatedWork W3164306936 @default.
• W4385562584 hasRelatedWork W3194558310 @default.
• W4385562584 hasRelatedWork W4287178724 @default.
• W4385562584 hasRelatedWork W4288238488 @default.
• W4385562584 hasRelatedWork W4320342417 @default.
• W4385562584 isParatext "false" @default.
• W4385562584 isRetracted "false" @default.
• W4385562584 workType "article" @default.