Online Dense Subgraph Discovery via Blurred-Graph Feedback

Dense subgraph discovery aims to find a dense component in edge-weighted graphs. This is a fundamental graph-mining task with a variety of applications and thus has received much attention recently. Although most existing methods assume that each individual edge weight is easily obtained, such an assumption is not necessarily valid in practice. In this paper, we introduce a novel learning problem for dense subgraph discovery in which a learner queries edge subsets rather than only single edges and observes a noisy sum of edge weights in a queried subset. For this problem, we first propose a polynomial-time algorithm that obtains a nearly-optimal solution with high probability. Moreover, to deal with large-sized graphs, we design a more scalable algorithm with a theoretical guarantee. Computational experiments using real-world graphs demonstrate the effectiveness of our algorithms.

[1]  Masashi Sugiyama,et al.  Fully adaptive algorithm for pure exploration in linear bandits , 2017, 1710.05552.

[2]  Divesh Srivastava,et al.  Dense subgraph maintenance under streaming edge weight updates for real-time story identification , 2012, The VLDB Journal.

[3]  Masashi Sugiyama,et al.  Polynomial-Time Algorithms for Multiple-Arm Identification with Full-Bandit Feedback , 2019, Neural Computation.

[4]  Kumar Chellapilla,et al.  Finding Dense Subgraphs with Size Bounds , 2009, WAW.

[5]  Lise Getoor,et al.  Privacy in Social Networks: A Survey , 2011, Social Network Data Analytics.

[6]  Y. Ye.  Approximating Quadratic Programming With Bound Constraints , 1997 .

[7]  Silvio Lattanzi,et al.  Improved Parallel Algorithms for Density-Based Network Clustering , 2019, ICML.

[8]  Peter Auer,et al.  Using Confidence Bounds for Exploitation-Exploration Trade-offs , 2003, J. Mach. Learn. Res..

[9]  Zhaonian Zou,et al.  Polynomial-Time Algorithm for Finding Densest Subgraphs in Uncertain Graphs , 2013 .

[10]  Moses Charikar,et al.  Greedy approximation algorithms for finding dense components in a graph , 2000, APPROX.

[11]  Charalampos E. Tsourakakis,et al.  Dense Subgraph Discovery: KDD 2015 tutorial , 2015, KDD.

[12]  Alessandro Lazaric,et al.  Best Arm Identification: A Unified Approach to Fixed Budget and Fixed Confidence , 2012, NIPS.

[13]  Yasushi Kawase,et al.  Graph Mining Meets Crowdsourcing: Extracting Experts for Answer Aggregation , 2019, IJCAI.

[14]  Christopher Ré,et al.  Managing Uncertainty in Social Networks , 2007, IEEE Data Eng. Bull..

[15]  Marco Pellegrini,et al.  Extraction and classification of dense communities in the web , 2007, WWW '07.

[16]  Charalampos E. Tsourakakis,et al.  Space- and Time-Efficient Algorithm for Maintaining Dense Subgraphs on One-Pass Dynamic Streams , 2015, STOC.

[17]  J. Kiefer,et al.  The Equivalence of Two Extremum Problems , 1960, Canadian Journal of Mathematics.

[18]  Guillaume Sagnol,et al.  Submodularity and Randomized rounding techniques for Optimal Experimental Design , 2010, Electron. Notes Discret. Math..

[19]  Ravi Kumar,et al.  Discovering Large Dense Subgraphs in Massive Graphs , 2005, VLDB.

[20]  Naonori Kakimura,et al.  Finding a Dense Subgraph with Sparse Cut , 2018, CIKM.

[21]  Aristides Gionis,et al.  Fully Dynamic Algorithm for Top-k Densest Subgraphs , 2017, CIKM.

[22]  Sofya Vorotnikova,et al.  Densest Subgraph in Dynamic Graph Streams , 2015, MFCS.

[23]  Jian Li,et al.  Pure Exploration of Multi-armed Bandit Under Matroid Constraints , 2016, COLT.

[24]  Uriel Feige,et al.  The Dense k -Subgraph Problem , 2001, Algorithmica.

[25]  Guillaume Sagnol,et al.  Approximation of a maximum-submodular-coverage problem involving spectral functions, with application to experimental designs , 2010, Discret. Appl. Math..

[26]  Sébastien Bubeck,et al.  Multiple Identifications in Multi-Armed Bandits , 2012, ICML.

[27]  Akiko Takeda,et al.  Robust Densest Subgraph Discovery , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[28]  Dimitris S. Papailiopoulos,et al.  Finding Dense Subgraphs via Low-Rank Bilinear Optimization , 2014, ICML.

[29]  Y. Nesterov.  Semidefinite relaxation and nonconvex quadratic optimization , 1998 .

[30]  Andrew V. Goldberg,et al.  Finding a Maximum Density Subgraph , 1984 .

[31]  Francesco Bonchi,et al.  Core Decomposition and Densest Subgraph in Multilayer Networks , 2017, CIKM.

[32]  Jakub W. Pachocki,et al.  Scalable Large Near-Clique Detection in Large-Scale Networks via Sampling , 2015, KDD.

[33]  Wei Chen,et al.  Combinatorial Pure Exploration of Multi-Armed Bandits , 2014, NIPS.

[34]  Michael Jackson,et al.  Optimal Design of Experiments , 1994 .

[35]  Yishay Mansour,et al.  Top-$k$ Combinatorial Bandits with Full-Bandit Feedback , 2020, ALT.

[36]  T.-H. Hubert Chan,et al.  Maintaining Densest Subsets Efficiently in Evolving Hypergraphs , 2017, CIKM.

[37]  Samir Khuller,et al.  On Finding Dense Subgraphs , 2009, ICALP.

[38]  Alessandro Lazaric,et al.  Best-Arm Identification in Linear Bandits , 2014, NIPS.

[39]  Sergei Vassilvitskii,et al.  Densest Subgraph in Streaming and MapReduce , 2012, Proc. VLDB Endow..

[40]  David P. Williamson,et al.  Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming , 1995, JACM.

[41]  Alexandra Carpentier,et al.  Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problem , 2016, COLT.

[42]  Wei Chen,et al.  Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications (Extended Version) , 2018, IJCAI.

[43]  Yehuda Lindell,et al.  Privacy Preserving Data Mining , 2002, Journal of Cryptology.

[44]  Takuro Fukunaga,et al.  Threshold Influence Model for Allocating Advertising Budgets , 2015, ICML.

[45]  Aditya Bhaskara,et al.  Detecting high log-densities: an O(n¼) approximation for densest k-subgraph , 2010, STOC '10.

[46]  Silvio Lattanzi,et al.  Efficient Densest Subgraph Computation in Evolving Graphs , 2015, WWW.

[47]  Gary D. Bader,et al.  An automated method for finding molecular complexes in large protein interaction networks , 2003, BMC Bioinformatics.

[48]  Sanjeev Mahajan,et al.  Derandomizing Approximation Algorithms Based on Semidefinite Programming , 1999, SIAM J. Comput..

[49]  Haiyuan Yu,et al.  Detecting overlapping protein complexes in protein-protein interaction networks , 2012, Nature Methods.

[50]  Patrick J. Wolfe,et al.  Subgraph Detection Using Eigenvector L1 Norms , 2010, NIPS.

[51]  Charalampos E. Tsourakakis.  The K-clique Densest Subgraph Problem , 2015, WWW.

[52]  Jakub W. Pachocki,et al.  Novel Dense Subgraph Discovery Primitives: Risk Aversion and Exclusion Queries , 2019, ECML/PKDD.

[53]  Csaba Szepesvári,et al.  Improved Algorithms for Linear Stochastic Bandits , 2011, NIPS.

[54]  Ruosong Wang,et al.  Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration , 2017, COLT.

[55]  R. Munos,et al.  Best Arm Identification in Multi-Armed Bandits , 2010, COLT.

[56]  Yasushi Kawase,et al.  The Densest Subgraph Problem with a Convex/Concave Size Function , 2017, Algorithmica.