Das Internet der Dinge (IoT) hat bereits begonnen, große Datenmengen zu generieren. Infrastrukturen, Maschinen, Fahrzeuge und Alltagsgegenstände wie Smartphones oder Fernseher sind mit intelligenten Funktionen ausgestattet, die miteinander verbunden sind. Diese Objekte enthalten Sensoren, RFID-Chips und Kameras, die kontinuierlich Daten produzieren und innerhalb dieser cyberphysikalischen Systeme (CPSs) kommunizieren. Eine natürliche Darstellung eines verknüpften Datensatzes wird durch einen Graphen bereitgestellt, wobei Entitäten als Knoten dargestellt werden und ihre Beziehungen durch Kanten kodiert werden. Im Vergleich zur klassischen Darstellung von Objekten als Merkmalsvektoren ermöglicht die Graphenstruktur zusätzlich die Darstellung der komplexen Beziehungen zwischen diesen Objekten. Das Projekt A6 beschäftigt sich mit der Entwicklung neuer Methoden zur Analyse von großen Graphen bzw. einer großen Anzahl von Graphen in ressourcenschwachen Umgebungen.
In der nächsten Phase möchten wir einige unserer Ergebnisse in reale Anwendungen einbringen und uns CPSs nähern. Darüber hinaus wollen wir uns auf Feature-Learning-Techniken für Graphen konzentrieren, d.h. unsere neuen Methoden basieren nicht mehr auf einem vorgegebenen Merkmalsraum, sondern das Lernen geeigneter Merkmale wird als Teil des Problems betrachtet. Zu diesem Zweck wollen wir auf unsere Ergebnisse aus Phase 2 zu effizienten Graphenkernen aufbauen und diese um Feature Learning erweitern. Zum Beispiel erweitern wir die Forschung von A6 auf das geometrische Deep Learning, das ein aufkommendes Feld ist, das die Techniken des Deep Learnings für Euklidische Domänen auf Graphen ausdehnt. Insbesondere möchten wir randomisierte Stichprobentechniken bei Problemen im Zusammenhang mit Graphkernen und auch beim geometrischen Deep Learning anwenden. Mit unserem Fokus auf CPSs wid die Analyse dynamischer Daten unter (weichen) Echtzeitanforderungen immer wichtiger. Daher werden wir Lernaufgaben an dynamischen Graphen wie Sequenzen und Streams von Graphen untersuchen. Um unsere neuen Methoden in CPSs zu integrieren, müssen unsere Ansätze Ressourcenbeschränkungen einhalten in Bezug auf Laufzeit, Speicher, Genauigkeit, Energie, Übertragungsgeschwindigkeit und Anzahl der markierten Daten. Wir werden unsere Methoden an spezifischen Systemen und Domänen evaluieren, die im SFB 876 relevant sind, wie logistische Sensor-Aktor-Netzwerke (A4), Verkehrsprognosen (B4) und der Analyse hochfrequenter unregelmäßiger strukturierter Daten (C3/C5).
| Bause/etal/2022a |
Franka Bause and Erich Schubert and Nils M. Kriege.
EmbAssi: embedding assignment costs for similarity search in large graph databases.
In
Data Mining and Knowledge Discovery,
Springer,
2022.
|
| Bause/etal/2021a |
Franka Bause and David B. Blumenthal and Erich Schubert and Nils M. Kriege.
Metric Indexing for Graph Similarity Search.
In
Similarity Search and Applications - 14th International Conference, SISAP 2021, Dortmund, Germany, September 29 - October 1, 2021, Proceedings,
Vol. 13058,
Seiten 323--336,
Springer,
2021.
|
| Bertram/etal/2021a |
Bertram, Nico and Ellert, Jonas and Fischer, Johannes.
Lyndon Words Accelerate Suffix Sorting.
In
Mutzel, Petra and Pagh, Rasmus and Herman, Grzegorz (editors),
29th Annual European Symposium on Algorithms (ESA 2021),
Vol. 204,
Seiten 15:1--15:13,
Dagstuhl, Germany,
Schloss Dagstuhl -- Leibniz-Zentrum für Informatik,
2021.
|
| Fey/etal/2021a |
Fey, M. and Lenssen, J. E. and Weichert, F. and Leskovec, J..
GNNAutoScale: Scalable And Expressive Graph Neural Networks via Historical Embeddings.
In
International Conference on Machine Learning (ICML),
2021.
|
| Hu/etal/2021a |
Hu, Weihua and Fey, Matthias and Hongyu, Ren and Nakata, Maho and Dong, Yuxiao and Leskovec, Jure.
OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs.
In
CoRR,
Vol. abs/2103.09430,
2021.
|
| Morris/etal/2021a |
Morris, Christopher and Fey, Matthias and Kriege, Nils M..
The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs.
In
International Joint Conferences on Artifical Intelligence - Survey Track,
2021.
|
| Fey/etal/2020a |
Fey, Matthias and Lenssen, Jan E. and Morris, Christopher and Masci, Jonathan and Kriege, Nils M..
Deep Graph Matching Consensus.
In
International Conference on Learning Representations (ICLR),
2020.
|
| Fey/etal/2020d |
Fey, Matthias and Yuen, Jan-Gin and Weichert, Frank.
Hierarchical Inter-Message Passing for Learning on Molecular Graphs.
In
ICML Graph Representation Learning and Beyond (GRL+) Workhop,
2020.
|
| Hu/etal/2020a |
Hu, Weihua and Fey, Matthias and Zitnik, Marinka and Dong, Yuxiao and Ren, Hongyu and Liu, Bowen and Catasta, Michele and Leskovec, Jure.
Open Graph Benchmark: Datasets for Machine Learning on Graphs.
In
CoRR,
Vol. abs/2005.00687,
2020.
|
| Kleineberg/etal/2020a |
Kleineberg, Marian and Fey, Matthias and Weichert, Frank.
Adversarial Generation of Continuous Implicit Shape Representations.
In
Eurographics - Short Papers,
2020.
|
| Kriege/etal/2020a |
Kriege, Nils M. and Johansson, Fredrik D. and Morris, Christopher.
A Survey on Graph Kernels.
In
Applied Network Science,
Vol. 5,
No. 1,
Seiten 6,
2020.
|
| Morris/etal/2020b |
Christopher Morris and Nils M. Kriege and Franka Bause and Kristian Kersting and Petra Mutzel and Marion Neumann.
TUDataset: A collection of benchmark datasets for learning with graphs.
In
ICML 2020 Workshop on Graph Representation Learning and Beyond (GRL+ 2020),
2020.
|
| Oettershagen/etal/2020a |
Oettershagen, Lutz and Kriege, Nils M. and Morris, Christopher and Mutzel, Petra.
Temporal Graph Kernels for Classifying Dissemination Processes.
In
SIAM International Conference on Data Mining (SDM),
2020.
|
| Fey/2019a |
Fey, Matthias.
Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks.
In
ICLR Workshop on Representation Learning on Graphs and Manifolds,
2019.
|
| Fey/Lenssen/2019a |
Fey, Matthias and Lenssen, Jan Eric.
Fast Graph Representation Learning with PyTorch Geometric.
In
ICLR Workshop on Representation Learning on Graphs and Manifolds,
2019.
|
| Giscard/etal/2019a |
Giscard, Pierre-Louis and Kriege, Nils M. and Wilson, Richard C..
A General Purpose Algorithm for Counting Simple Cycles and Simple Paths of Any Length.
In
Algorithmica,
Vol. 81,
No. 7,
Seiten 2716--2737,
2019.
|
| Kriege/2019a |
Nils M. Kriege.
Deep Weisfeiler-Lehman Assignment Kernels via Multiple Kernel Learning.
In
27th European Symposium on Artificial Neural Networks, ESANN,
2019.
|
| Kriege/etal/2019a |
Kriege, Nils M. and Johansson, Fredrik D. and Morris, Christopher.
A Survey on Graph Kernels.
In
CoRR,
Vol. abs/1903.11835,
2019.
|
| Kriege/etal/2019b |
Kriege, Nils M. and Giscard, Pierre-Louis and Bause, Franka and Wilson, Richard C..
Computing Optimal Assignments in Linear Time for Graph Matching.
In
CoRR,
Vol. abs/1901.10356,
2019.
|
| Kriege/etal/2019c |
Kriege, Nils M. and Neumann, Marion and Morris, Christopher and Kersting, Kristian and Mutzel, Petra.
A unifying view of explicit and implicit feature maps of graph kernels.
In
Data Mining and Knowledge Discovery,
Vol. 33,
No. 8,
Seiten 1505--1547,
2019.
|
| Kriege/etal/2019d |
Kriege, Nils M. and Giscard, Pierre-Louis and Bause, Franka and Wilson, Richard C..
Computing Optimal Assignments in Linear Time for Approximate Graph Matching.
In
IEEE International Conference on Data Mining (ICDM),
2019.
|
| Morris/etal/2019a |
Morris, Christopher and Ritzert, Martin and Fey, Matthias and Hamilton, William L. and Lenssen, Jan Eric and Rattan, Gaurav and Grohe, Martin.
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks.
In
AAAI Conference on Artificial Intelligence (AAAI),
2019.
|
| Oettershagen/etal/2019a |
Oettershagen, Lutz and Kriege, Nils M. and Morris, Christopher and Mutzel, Petra.
Temporal Graph Kernels for Classifying Dissemination Processes.
In
CoRR,
Vol. abs/1911.05496,
2019.
|
| Stoecker/etal/2019a |
Bianca K. St\"ocker and Till Sch\"afer and Petra Mutzel and Johannes K\"oster and Nils M. Kriege and Sven Rahmann.
Protein Complex Similarity Based on Weisfeiler-Lehman Labeling.
In
Giuseppe Amato and Claudio Gennaro and Vincent Oria and Milos Radovanovic (editors),
Similarity Search and Applications,
Seiten 308--322,
Cham,
Springer,
2019.
title = {Protein Complex Similarity Based on {W}eisfeiler-{L}ehman Labeling}, address = {Cham}, booktitle = {Similarity Search and Applications}, editor = {Giuseppe Amato and Claudio Gennaro and Vincent Oria and Milos Radovanovic}, year = {2019}, pages = {308--322}, publisher = {Springer International Publishing}, isbn = {978-3-030-32047-8}, abstract = {Proteins in living cells rarely act alone, but instead perform their functions together with other proteins in so-called protein complexes. Being able to quantify the similarity between two protein complexes is essential for numerous applications, e.g. for database searches of complexes that are similar to a given input complex. While the similarity problem has been extensively studied on single proteins and protein families, there is very little existing work on modeling and computing the similarity between protein complexes. Because protein complexes can be naturally modeled as graphs, in principle general graph similarity measures may be used, but these are often computationally hard to obtain and do not take typical properties of protein complexes into account. Here we propose a parametric family of similarity measures based on Weisfeiler-Lehman labeling. We evaluate it on simulated complexes of the extended human integrin adhesome network. We show that the defined family of similarity measures is in good agreement with edit similarity, a similarity measure derived from graph edit distance, but can be computed more efficiently. It can therefore be used in large-scale studies and serve as a basis for further refinements of modeling protein complex similarity.} }')">
|
| CohenSteiner/etal/2017a |
Cohen-Steiner, David and Kong, Weihao and Sohler, Christian and Valiant, Gregory.
Approximating the Spectrum of a Graph.
In
24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD),
2018.
|
| Fey/etal/2018a |
Fey, Matthias and Lenssen, Jan Eric and Weichert, Frank and Müller, Heinrich.
SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels.
In
IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
2018.
|
| Kriege/etal/2018b |
Kriege, Nils and Morris, Christopher and Rey, Anja and Sohler, Christian.
A Property Testing Framework for the Theoretical Expressivity of Graph Kernels.
In
International Joint Conference on Artificial Intelligence (IJCAI),
2018.
|
| Kriege/etal/2018c |
Kriege, Nils and Fey, Matthias and Fisseler, Denis and Mutzel, Petra and Weichert, Frank.
Recognizing Cuneiform Signs Using Graph Based Methods.
In
International Workshop on Cost-Sensitive Learning (COST), SIAM International Conference on Data Mining (SDM),
2018.
|
| Lenssen/etal/2018b |
Lenssen, Jan Eric and Fey, Matthias and Libuschewski, Pascal.
Group Equivariant Capsule Networks.
In
Advances in Neural Information Processing Systems (NeurIPS) 31,
Seiten 8844--8853,
Curran Associates, Inc.,
2018.
|
| Stoecker/etal/2018a |
Stöcker, Bianca K. and Schäfer, Till and Mutzel, Petra and Köster, Johannes and Kriege, Nils and Rahmann, Sven.
Protein Complex Similarity Based on Weisfeiler-Lehman Labeling.
In
PeerJ Preprints,
Vol. 6,
No. e26612,
2018.
|
| Ying/etal/2018a |
Ying, Rex and You, Jiaxuan and Morris, Christopher and Ren, Xiang and Hamilton, William L. and Leskovec, Jure.
Hierarchical Graph Representation Learning with Differentiable Pooling.
In
Neural Information Processing Systems (NIPS) 2019,
2018.
|
| Biedl/Chimani/2017a |
Biedl, Therese and Chimani, Markus and Derka, Martin and Mutzel, Petra.
Crossing Number for Graphs With Bounded Pathwidth.
In
Yoshio Okamoto and Takeshi Tokuyama (editors),
Algorithms and Computation - 28th International Symposium, ISAAC 2017,
Vol. 92,
Seiten 1-13,
Dagstuhl, Germany,
Schloss Dagstuhl - Leibniz-Zentrum für Informatik,
2017.
|
| Boekler/etal/2017a |
Bökler, Fritz and Ehrgott, Matthias and Morris, Christopher and Mutzel, Petra.
Output-sensitive complexity of multiobjective combinatorial optimization.
In
Journal of Multi-Criteria Decision Analysis,
Vol. 24,
No. 1-2,
2017.
|
| Kriege/etal/2017a |
Kriege, Nils and Neumann, Marion and Morris, Christopher and Kersting, Kristian and Mutzel, Petra.
A Unifying View of Explicit and Implicit Feature Maps for Structured Data: Systematic Studies of Graph Kernels.
In
CoRR,
Vol. abs/1703.00676,
2017.
|
| Molina/etal/2017a |
Molina, Alejandro and Natarajan, Sriraam and Kersting, Kristian.
Poisson Sum-Product Networks: A Deep Architecture for Tractable Multivariate Poisson Distributions.
In
Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI),
Seiten 2357--2363,
2017.
|
| Morris/etal/2017a |
Morris, Christopher and Kersting, Kristian and Mutzel, Petra.
Global Weisfeiler-Lehman Graph Kernels.
In
CoRR,
2017.
|
| Morris/etal/2017b |
Morris, Christopher and Kersting, Kristian and Mutzel, Petra.
Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs.
In
IEEE International Conference on Data Mining (ICDM),
Seiten 327--336,
2017.
|
| Morris/Kriege/2016a |
Kriege, Nils and Morris, Christopher.
Recent Advances in Kernel-Based Graph Classification.
In
Michelangelo Ceci and Jaakko Hollmen and Ljupčo Todorovski and Celine Vens (editors),
European Conference on Machine Learning & Principles and Practice of Knowledge Discovery in Databases (ECML PKDD),
Springer,
2017.
|
| Bauckhage/Kersting/2016a |
Bauckhage, Christian and Kersting, Kristian.
Collective Attention on the Web.
In
Foundations and Trends in Web Science,
Vol. 5,
No. 1-2,
Seiten 1-136,
2016.
|
| Das/etal/2016a |
Das, Mayukh and Wu, Yunqing and Khot, Tushar and Kersting, Kristian and Natarajan, Sriraam.
Scaling Lifted Probabilistic Inference and Learning Via Graph Databases,.
In
Proceedings of the SIAM International Conference on Data Mining (SDM),
2016.
|
| Erdmann/etal/2016b |
Erdmann, Elena and Boczek, Karin and Koppers, Lars and von Nordheim, Gerret and Poelitz, Christian and Molina, Alejandro and Morik, Katharina and Mueller, Henrik and Rahnenfuehrer, Joerg and Kersting, Kristian.
Machine Learning meets Data-Driven Journalism: Boosting International Understanding and Transparency in News Coverage.
In
Proceedings of the 2016 ICML Workshop on #Data4Good: Machine Learning in Social Good Applications,
2016.
|
| Giscard/etal/2016a |
Pierre-Louis Giscard and Nils Kriege and Richard C. Wilson.
A general purpose algorithm for counting simple cycles and simple paths of any length.
In
CoRR,
Vol. abs/1612.05531,
2016.
|
| Kriege/etal/2016a |
Kriege, Nils and Giscard, Pierre-Louis and Wilson, Richard C..
On Valid Optimal Assignment Kernels and Applications to Graph Classification.
In
CoRR,
Vol. abs/1606.01141,
2016.
|
| Kriege/etal/2016b |
Kriege, Nils and Giscard, Pierre-Louis and Wilson, Richard C..
On Valid Optimal Assignment Kernels and Applications to Graph Classification.
In
Advances in Neural Information Processing Systems (NIPS),
Seiten 1623--1631,
2016.
|
| Mladenov/etal/2016a |
Mladenov, Martin and Heinrich, Danny and Kleinhans, Leonard and Gonsior, Felix and Kersting, Kristian.
RELOOP: A Python-Embedded Declarative Language for Relational Optimization.
In
Working Notes of the First AAAI Workshop on Declarative Learning Based Programming (DeLBP),
AAAI Press,
2016.
|
| Morris/etal/2016a |
Morris, Christopher and Kriege, Nils and Kersting, Kristian and Mutzel, Petra.
Faster Kernels for Graphs with Continuous Attributes via Hashing.
In
IEEE International Conference on Data Mining (ICDM),
Seiten 1095--1100,
2016.
|
| Neumann/Garnett/2016a |
Neumann, Marion and Garnett, Roman and Bauckhage, Christian and Kersting, Kristian.
Propagation Kernels: Efficient Graph Kernels from Propagated Information.
In
Machine Learning,
Vol. 102,
No. 2,
Seiten 209--245,
2016.
|
| Szymanski/etal/2016a |
Szymanski, Piotr and Kajdanowicz, Tomasz and Kersting, Kristian.
How Is a Data-Driven Approach Better than Random Choice in Label Space Division for Multi-Label Classification?.
In
Entropy,
Vol. 18,
No. 8,
Seiten 282,
2016.
|
| Bauckhage/etal/2015a |
Bauckhage, Christian and Kersting, Kristian and Hadiji, Fabian.
Parameterizing the Distance Distribution of Undirected Networks.
In
Tom Heskes and Marina Meila (editors),
Proceedings of the 31th Conference on Uncertainty in Artificial Intelligence (UAI),
AUAI,
2015.
|
| Bauckhage/etal/2015b |
Bauckhage, Christian and Kersting, Kristian and Hadiji, Fabian.
How Viral are Viral Movies?.
In
Proceedings of the 9th International AAAI Conference on Web and Social Media (ICWSM),
2015.
|
| Fey/2022a |
Mathias Fey.
On the power of message passing for learning on graph-structured data.
TU Dortmund,
2022.
|
| Kriege/2015a |
Nils Morten Kriege.
Comparing Graphs: Algorithms & Applications.
Department of Computer Science, TU Dortmund,
2015.
|
| Kersting/etal/2014a |
Kersting, Kristian and Mladenov, Martin and Garnett, Roman and Grohe, Martin.
Power Iterated Color Refinement.
In
Brodley, Carla and Stone, Peter (editors),
Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI-14),
AAAI Press,
2014.
|
| Kriege/etal/2014a |
Kriege, Nils and Neumann, Marion and Kersting, Kristian and Mutzel, Petra.
Explicit versus Implicit Graph Feature Maps: A Computational Phase Transition for Walk Kernels.
In
Kumar, Ravi and Toivonen, Hannu (editors),
Proceedings of the IEEE International Conference on Data Mining (ICDM),
Seiten 881--886,
IEEE,
2014.
|
| Bauckhage/etal/2013b |
Bauckhage, Christian and Kersting, Kristian and Rastegarpanah, Bashir.
The Weibull as a Model of Shortest Path Distributions in Random Networks.
In
L. Adamic and L. Getoor and B. Huang and J. Leskovec and J. McAuley (editors),
Working Notes of the International Workshop on Mining and Learning with Graphs,
Chicago, IL, USA,
2013.
|
| Gronemann/etal/2013a |
M. Gronemann and M. Jünger and P. Mutzel and N. Kriege.
MolMap -- Visualizing Molecule Libraries as Topographic Maps.
In
Proc.\ Int. Conf. Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications (GRAPP & IVAPP),
2013.
|
| Neumann/etal/2013a |
M. Neumann and R. Garnett and K. Kersting.
Coinciding Walk Kernels: Parallel Absorbing Random Walks for Learning with Graphs and Few Labels.
In
Cheng Soon Ong and Tu Bao Ho (editors),
Proceedings of the 5th Annual Asian Conference on Machine Learning (ACML 2013),
Vol. 29,
Seiten 357-372,
2013.
|
| Newman/Sohler/2013a |
I. Newman and C. Sohler.
Every Property of Hyperfinite Graphs Is Testable.
In
SIAM Journal on Computing,
Vol. 42,
No. 3,
Seiten 1095-1112,
2013.
|
| Kriege/Mutzel/2012a |
Kriege, N. and Mutzel, P..
Subgraph Matching Kernels for Attributed Graphs.
In
Proceedings of the 29th International Conference on Machine Learning (ICML),
Omnipress,
2012.
|
| Neumann/etal/2012a |
M. Neumann and N. Patricia and R. Garnett and K. Kersting.
Efficient Graph Kernels by Randomization.
In
P. Flach and T. De Bie and N. Cristianini (editors),
Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2012),
Bristol, UK,
Springer,
2012.
|
| Czumaj/etal/2011a |
A. Czumaj and M. Monemizadeh and K. Onak and C. Sohler.
Planar Graphs: Random Walks and Bipartiteness Testing.
In
Proceedings of the 52nd Annual IEEE Symposium on Foundations of Computer Science,
Seiten 423-432,
2011.
|
| Klein/etal/2011a |
Klein, K. and Kriege, N. and Mutzel, P..
CT-index: Fingerprint-based Graph Indexing Combining Cycles and Trees.
In
IEEE 27th Int. Conf. on Data Engineering (ICDE),
Seiten 1115--1126,
2011.
|
| Czumaj/Sohler/2010a |
A. Czumaj and C. Sohler.
Testing Expansion in Bounded-Degree Graphs.
In
Combinatorics, Probability & Computing,
Vol. 19,
No. 5-6,
Seiten 693-709,
2010.
|
| Czumaj/etal/2009a |
A. Czumaj and A. Shapira and C. Sohler.
Testing Hereditary Properties of Nonexpanding Bounded-Degree Graphs.
In
SIAM Journal on Computing,
Vol. 38,
No. 6,
Seiten 2499-2510,
2009.
|
| Ljubic/etal/2006a |
Ljubi\'c, I. and Weiskircher, R. and Pferschy, U. and Klau, G. and Mutzel, P. and Fischetti, M..
An Algorithmic Framework for the Exact Solution of the Prize-Collecting Steiner Tree Problem.
In
Mathematical Programming,
Vol. Series B 105,
Seiten 427-449,
2006.
|
