publication . Preprint . Conference object . 2018

Adaptive Graph Convolutional Neural Networks

Junzhou Huang;
Open Access English
  • Published: 09 Jan 2018
Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and flexible graph CNN taking data of arbitrary graph structure as input. In that way a task-driven adaptive graph is learned for each graph data while training. To efficiently learn the graph, a distance metric learning is proposed. Extensive experiments on nine graph-structured datasets have demonstrate...
arXiv: Computer Science::Neural and Evolutionary Computation
ACM Computing Classification System: MathematicsofComputing_DISCRETEMATHEMATICS
free text keywords: Computer Science - Learning, Statistics - Machine Learning
Related Organizations
Funded by
NSF| Statistics-based Optimization Methods for Adaptive Interdisciplinary Pain Management
  • Funder: National Science Foundation (NSF)
  • Project Code: 1434401
  • Funding stream: Directorate for Engineering | Division of Civil, Mechanical & Manufacturing Innovation
NSF| CI-P: Planning for SMART-MOVE: A Spatiotemporal Annotated Human Activity Repository for Advanced Motion Recognition and Analysis Research
  • Funder: National Science Foundation (NSF)
  • Project Code: 1405985
  • Funding stream: Directorate for Computer & Information Science & Engineering | Division of Computer and Network Systems
NSF| RI: Small: Collaborative Research: A Topological Analysis of Uncertainly Representation in the Brain
  • Funder: National Science Foundation (NSF)
  • Project Code: 1718853
  • Funding stream: Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems
NSF| III: Small: Collaborative Research: Robust Materials Genome Data Mining Framework for Prediction and Guidance of Nanoparticle Synthesis
  • Funder: National Science Foundation (NSF)
  • Project Code: 1423056
  • Funding stream: Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems
31 references, page 1 of 3

[Altae-Tran et al. 2016] Altae-Tran, H.; Ramsundar, B.; Pappu, A. S.; and Pande, V. 2016. Low data drug discovery with one-shot learning. arXiv preprint arXiv:1611.03199.

[Bruna et al. 2013] Bruna, J.; Zaremba, W.; Szlam, A.; and LeCun, Y. 2013. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203.

[Chung 1997] Chung, F. R. 1997. Spectral graph theory.

Number 92. American Mathematical Soc.

[De Brabandere et al. 2016] De Brabandere, B.; Jia, X.; Tuytelaars, T.; and Van Gool, L. 2016. Dynamic filter networks. In Neural Information Processing Systems (NIPS). [OpenAIRE]

[Defferrard, Bresson, and Vandergheynst 2016] Defferrard, M.; Bresson, X.; and Vandergheynst, P. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in Neural Information Processing Systems, 3837-3845.

[Delaney 2004] Delaney, J. S. 2004. Esol: estimating aqueous solubility directly from molecular structure. Journal of chemical information and computer sciences 44(3):1000-1005.

[Dix et al. 2006] Dix, D. J.; Houck, K. A.; Martin, M. T.; Richard, A. M.; Setzer, R. W.; and Kavlock, R. J. 2006. The toxcast program for prioritizing toxicity testing of environmental chemicals. Toxicological Sciences 95(1):5-12.

[Dundar et al. 2015] Dundar, M.; Kou, Q.; Zhang, B.; He, Y.; and Rajwa, B. 2015. Simplicity of kmeans versus deepness of deep learning: A case of unsupervised feature learning with limited data. In Machine Learning and Applications (ICMLA), 2015 IEEE 14th International Conference on, 883- 888. IEEE.

[Duvenaud et al. 2015] Duvenaud, D. K.; Maclaurin, D.; Iparraguirre, J.; Bombarell, R.; Hirzel, T.; Aspuru-Guzik, A.; and Adams, R. P. 2015. Convolutional networks on graphs for learning molecular fingerprints. In Advances in neural information processing systems, 2224-2232. [OpenAIRE]

[Gadde et al. 2016] Gadde, R.; Jampani, V.; Kiefel, M.; Kappler, D.; and Gehler, P. V. 2016. Superpixel convolutional networks using bilateral inceptions. In European Conference on Computer Vision, 597-613. Springer. [OpenAIRE]

[Gomes et al. 2017] Gomes, J.; Ramsundar, B.; Feinberg, E. N.; and Pande, V. S. 2017. Atomic convolutional networks for predicting protein-ligand binding affinity. arXiv preprint arXiv:1703.10603. [OpenAIRE]

[Henaff, Bruna, and LeCun 2015] Henaff, M.; Bruna, J.; and LeCun, Y. 2015. Deep convolutional networks on graphstructured data. arXiv preprint arXiv:1506.05163.

[Hinton et al. 2012] Hinton, G.; Deng, L.; Yu, D.; Dahl, G. E.; Mohamed, A.-r.; Jaitly, N.; Senior, A.; Vanhoucke, V.; Nguyen, P.; Sainath, T. N.; et al. 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine 29(6):82-97.

[Ioffe and Szegedy 2015] Ioffe, S., and Szegedy, C. 2015.

31 references, page 1 of 3
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue