LEADER 04262nam 22006615 450 001 9910725098703321 005 20251009080451.0 010 $a9789819901845$b(electronic book) 010 $a9789819901852 010 $a9819901855 024 7 $a10.1007/978-981-99-0185-2 035 $a(CKB)5580000000542371 035 $a(MiAaPQ)EBC30544995 035 $a(Au-PeEL)EBL30544995 035 $a(DE-He213)978-981-99-0185-2 035 $a(PPN)270615695 035 $a(OCoLC)1380015458 035 $a(ODN)ODN0010070572 035 $a(EXLCZ)995580000000542371 100 $a20230515d2023 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aHypergraph Computation /$fby Qionghai Dai, Yue Gao 205 $a1st ed. 2023. 210 1$aSingapore :$cSpringer Nature Singapore :$cImprint: Springer,$d2023. 215 $a1 online resource (xv, 244 pages) $cillustrations 225 1 $aArtificial Intelligence: Foundations, Theory, and Algorithms,$x2365-306X 311 0 $a9789819901845 311 0 $a9819901847 320 $aIncludes bibliographical refences 327 $aChapter 1. Introduction -- Chapter 2. Mathematical Foundations of Hypergraph -- Chapter 3. Hypergraph Computation Paradigms -- 4. Hypergraph Modeling -- Chapter 5. Typical Hypergraph Computation Tasks -- 6. Hypergraph Structure Evolution -- Chapter 7. Neural Networks on Hypergraph -- Chapter 8. Large Scale Hypergraph Computation -- Chapter 9. Hypergraph Computation for Social Media Analysis -- Chapter 10. Hypergraph Computation for Medical and Biological Applications -- Chapter 11. Hypergraph Computation for Computer Vision -- Chapter 12.The Deep Hypergraph Library -- Chapter 13. Conclusions and Future Work. 330 $aThis open access book discusses the theory and methods of hypergraph computation. Many underlying relationships among data can be represented using graphs, for example in the areas including computer vision, molecular chemistry, molecular biology, etc. In the last decade, methods like graph-based learning and neural network methods have been developed to process such data, they are particularly suitable for handling relational learning tasks. In many real-world problems, however, relationships among the objects of our interest are more complex than pair-wise. Naively squeezing the complex relationships into pairwise ones will inevitably lead to loss of information which can be expected valuable for learning tasks. Hypergraph, as a generation of graph, has shown superior performance on modelling complex correlations compared with graph. Recent years have witnessed a great popularity of researches on hypergraph-related AI methods, which have been used in computer vision, social media analysis, etc. We summarize these attempts as a new computing paradigm, called hypergraph computation, which is to formulate the high-order correlations underneath the data using hypergraph, and then conduct semantic computing on the hypergraph for different applications. The content of this book consists of hypergraph computation paradigms, hypergraph modelling, hypergraph structure evolution, hypergraph neural networks, and applications of hypergraph computation in different fields. We further summarize recent achievements and future directions on hypergraph computation in this book. 410 0$aArtificial Intelligence: Foundations, Theory, and Algorithms,$x2365-306X 606 $aArtificial intelligence 606 $aMachine learning 606 $aArtificial intelligence$xData processing 606 $aArtificial Intelligence 606 $aMachine Learning 606 $aData Science 615 0$aArtificial intelligence. 615 0$aMachine learning. 615 0$aArtificial intelligence$xData processing. 615 14$aArtificial Intelligence. 615 24$aMachine Learning. 615 24$aData Science. 676 $a006.3 686 $aCOM004000$aCOM031000$2bisacsh 700 $aDai$b Qionghai$0951993 702 $aGao$b Yue 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bOD$ 912 $a9910725098703321 996 $aHypergraph Computation$93403958 997 $aUNINA