1. CMU SCS Graph Mining: Laws, Generators and Tools Christos Faloutsos CMU

2. CMU SCS GATech 08C. Faloutsos 2 Thank you! Amy Bruckman Francine Lyken

3. CMU SCS GATech 08C. Faloutsos 3 Outline Problem definition / Motivation Static & dynamic laws; generators Tools: CenterPiece graphs; Tensors Other projects (Virus propagation, e-bay fraud detection) Conclusions

4. CMU SCS GATech 08C. Faloutsos 4 Motivation Data mining: ~ find patterns (rules, outliers) Problem#1: How do real graphs look like? Problem#2: How do they evolve? Problem#3: How to generate realistic graphs TOOLS Problem#4: Who is the ‘master-mind’? Problem#5: Track communities over time

5. CMU SCS GATech 08C. Faloutsos 5 Problem#1: Joint work with Dr. Deepayan Chakrabarti (CMU/Yahoo R.L.)

6. CMU SCS GATech 08C. Faloutsos 6 Graphs - why should we care? Internet Map [lumeta.com] Food Web [Martinez ’91] Protein Interactions [genomebiology.com] Friendship Network [Moody ’01]

7. CMU SCS GATech 08C. Faloutsos 7 Graphs - why should we care? IR: bi-partite graphs (doc-terms) web: hyper-text graph... and more: D1D1 DNDN T1T1 TMTM...

8. CMU SCS GATech 08C. Faloutsos 8 Graphs - why should we care? network of companies & board-of-directors members ‘viral’ marketing web-log (‘blog’) news propagation computer network security: email/IP traffic and anomaly detection....

9. CMU SCS GATech 08C. Faloutsos 9 Problem #1 - network and graph mining How does the Internet look like? How does the web look like? What is ‘normal’/‘abnormal’? which patterns/laws hold?

10. CMU SCS GATech 08C. Faloutsos 10 Graph mining Are real graphs random?

11. CMU SCS GATech 08C. Faloutsos 11 Laws and patterns Are real graphs random? A: NO!! –Diameter –in- and out- degree distributions –other (surprising) patterns

12. CMU SCS GATech 08C. Faloutsos 12 Solution#1 Power law in the degree distribution [SIGCOMM99] log(rank) log(degree) -0.82 internet domains att.com ibm.com

13. CMU SCS GATech 08C. Faloutsos 13 Solution#1’: Eigen Exponent E A2: power law in the eigenvalues of the adjacency matrix E = -0.48 Exponent = slope Eigenvalue Rank of decreasing eigenvalue May 2001

14. CMU SCS GATech 08C. Faloutsos 14 Solution#1’: Eigen Exponent E [Papadimitriou, Mihail, ’02]: slope is ½ of rank exponent E = -0.48 Exponent = slope Eigenvalue Rank of decreasing eigenvalue May 2001

15. CMU SCS GATech 08C. Faloutsos 15 But: How about graphs from other domains?

16. CMU SCS GATech 08C. Faloutsos 16 The Peer-to-Peer Topology Count versus degree Number of adjacent peers follows a power-law [Jovanovic+]

17. CMU SCS GATech 08C. Faloutsos 17 More power laws: citation counts: (citeseer.nj.nec.com 6/2001) log(#citations) log(count) Ullman

18. CMU SCS GATech 08C. Faloutsos 18 More power laws: web hit counts [w/ A. Montgomery] Web Site Traffic log(in-degree) log(count) Zipf users sites ``ebay’’

19. CMU SCS GATech 08C. Faloutsos 19 epinions.com who-trusts-whom [Richardson + Domingos, KDD 2001] (out) degree count trusts-2000-people user

20. CMU SCS GATech 08C. Faloutsos 20 Motivation Data mining: ~ find patterns (rules, outliers) Problem#1: How do real graphs look like? Problem#2: How do they evolve? Problem#3: How to generate realistic graphs TOOLS Problem#4: Who is the ‘master-mind’? Problem#5: Track communities over time

21. CMU SCS GATech 08C. Faloutsos 21 Problem#2: Time evolution with Jure Leskovec (CMU/MLD) and Jon Kleinberg (Cornell – sabb. @ CMU)

22. CMU SCS GATech 08C. Faloutsos 22 Evolution of the Diameter Prior work on Power Law graphs hints at slowly growing diameter: –diameter ~ O(log N) –diameter ~ O(log log N) What is happening in real data?

23. CMU SCS GATech 08C. Faloutsos 23 Evolution of the Diameter Prior work on Power Law graphs hints at slowly growing diameter: –diameter ~ O(log N) –diameter ~ O(log log N) What is happening in real data? Diameter shrinks over time

24. CMU SCS GATech 08C. Faloutsos 24 Diameter – ArXiv citation graph Citations among physics papers 1992 –2003 One graph per year time [years] diameter

25. CMU SCS GATech 08C. Faloutsos 25 Diameter – “Autonomous Systems” Graph of Internet One graph per day 1997 – 2000 number of nodes diameter

26. CMU SCS GATech 08C. Faloutsos 26 Diameter – “Affiliation Network” Graph of collaborations in physics – authors linked to papers 10 years of data time [years] diameter

27. CMU SCS GATech 08C. Faloutsos 27 Diameter – “Patents” Patent citation network 25 years of data time [years] diameter

28. CMU SCS GATech 08C. Faloutsos 28 Temporal Evolution of the Graphs N(t) … nodes at time t E(t) … edges at time t Suppose that N(t+1) = 2 * N(t) Q: what is your guess for E(t+1) =? 2 * E(t)

29. CMU SCS GATech 08C. Faloutsos 29 Temporal Evolution of the Graphs N(t) … nodes at time t E(t) … edges at time t Suppose that N(t+1) = 2 * N(t) Q: what is your guess for E(t+1) =? 2 * E(t) A: over-doubled! –But obeying the ``Densification Power Law’’

30. CMU SCS GATech 08C. Faloutsos 30 Densification – Physics Citations Citations among physics papers 2003: –29,555 papers, 352,807 citations N(t) E(t) ??

31. CMU SCS GATech 08C. Faloutsos 31 Densification – Physics Citations Citations among physics papers 2003: –29,555 papers, 352,807 citations N(t) E(t) 1.69

32. CMU SCS GATech 08C. Faloutsos 32 Densification – Physics Citations Citations among physics papers 2003: –29,555 papers, 352,807 citations N(t) E(t) 1.69 1: tree

33. CMU SCS GATech 08C. Faloutsos 33 Densification – Physics Citations Citations among physics papers 2003: –29,555 papers, 352,807 citations N(t) E(t) 1.69 clique: 2

34. CMU SCS GATech 08C. Faloutsos 34 Densification – Patent Citations Citations among patents granted 1999 –2.9 million nodes –16.5 million edges Each year is a datapoint N(t) E(t) 1.66

35. CMU SCS GATech 08C. Faloutsos 35 Densification – Autonomous Systems Graph of Internet 2000 –6,000 nodes –26,000 edges One graph per day N(t) E(t) 1.18

36. CMU SCS GATech 08C. Faloutsos 36 Densification – Affiliation Network Authors linked to their publications 2002 –60,000 nodes 20,000 authors 38,000 papers –133,000 edges N(t) E(t) 1.15

37. CMU SCS GATech 08C. Faloutsos 37 Motivation Data mining: ~ find patterns (rules, outliers) Problem#1: How do real graphs look like? Problem#2: How do they evolve? Problem#3: How to generate realistic graphs TOOLS Problem#4: Who is the ‘master-mind’? Problem#5: Track communities over time

38. CMU SCS GATech 08C. Faloutsos 38 Problem#3: Generation Given a growing graph with count of nodes N 1, N 2, … Generate a realistic sequence of graphs that will obey all the patterns

39. CMU SCS GATech 08C. Faloutsos 39 Problem Definition Given a growing graph with count of nodes N 1, N 2, … Generate a realistic sequence of graphs that will obey all the patterns –Static Patterns Power Law Degree Distribution Power Law eigenvalue and eigenvector distribution Small Diameter –Dynamic Patterns Growth Power Law Shrinking/Stabilizing Diameters

40. CMU SCS GATech 08C. Faloutsos 40 Problem Definition Given a growing graph with count of nodes N 1, N 2, … Generate a realistic sequence of graphs that will obey all the patterns Idea: Self-similarity –Leads to power laws –Communities within communities –…

41. CMU SCS GATech 08C. Faloutsos 41 Adjacency matrix Kronecker Product – a Graph Intermediate stage Adjacency matrix

42. CMU SCS GATech 08C. Faloutsos 42 Kronecker Product – a Graph Continuing multiplying with G 1 we obtain G 4 and so on … G 4 adjacency matrix

43. CMU SCS GATech 08C. Faloutsos 43 Kronecker Product – a Graph Continuing multiplying with G 1 we obtain G 4 and so on … G 4 adjacency matrix

44. CMU SCS GATech 08C. Faloutsos 44 Kronecker Product – a Graph Continuing multiplying with G 1 we obtain G 4 and so on … G 4 adjacency matrix

45. CMU SCS GATech 08C. Faloutsos 45 Properties: We can PROVE that –Degree distribution is multinomial ~ power law –Diameter: constant –Eigenvalue distribution: multinomial –First eigenvector: multinomial See [Leskovec+, PKDD’05] for proofs

46. CMU SCS GATech 08C. Faloutsos 46 Problem Definition Given a growing graph with nodes N 1, N 2, … Generate a realistic sequence of graphs that will obey all the patterns –Static Patterns Power Law Degree Distribution Power Law eigenvalue and eigenvector distribution Small Diameter –Dynamic Patterns Growth Power Law Shrinking/Stabilizing Diameters First and only generator for which we can prove all these properties

47. CMU SCS GATech 08C. Faloutsos 47 Stochastic Kronecker Graphs Create N 1  N 1 probability matrix P 1 Compute the k th Kronecker power P k For each entry p uv of P k include an edge (u,v) with probability p uv 0.40.2 0.10.3 P1P1 Instance Matrix G 2 0.160.08 0.04 0.120.020.06 0.040.020.120.06 0.010.03 0.09 PkPk flip biased coins Kronecker multiplication skip

48. CMU SCS GATech 08C. Faloutsos 48 Experiments How well can we match real graphs? –Arxiv: physics citations: 30,000 papers, 350,000 citations 10 years of data –U.S. Patent citation network 4 million patents, 16 million citations 37 years of data –Autonomous systems – graph of internet Single snapshot from January 2002 6,400 nodes, 26,000 edges We show both static and temporal patterns

49. CMU SCS GATech 08C. Faloutsos 49 Arxiv – Degree Distribution degree count Real graph Deterministic Kronecker Stochastic Kronecker

50. CMU SCS GATech 08C. Faloutsos 50 Arxiv – Scree Plot Rank Eigenvalue Real graph Deterministic Kronecker Stochastic Kronecker

51. CMU SCS GATech 08C. Faloutsos 51 Arxiv – Densification Nodes(t) Edges Real graph Deterministic Kronecker Stochastic Kronecker

52. CMU SCS GATech 08C. Faloutsos 52 Arxiv – Effective Diameter Nodes(t) Diameter Real graph Deterministic Kronecker Stochastic Kronecker

53. CMU SCS GATech 08C. Faloutsos 53 (Q: how to fit the parm’s?) A: Stochastic version of Kronecker graphs + Max likelihood + Metropolis sampling [Leskovec+, ICML’07]

54. CMU SCS GATech 08C. Faloutsos 54 Experiments on real AS graph Degree distributionHop plot Network valueAdjacency matrix eigen values

55. CMU SCS GATech 08C. Faloutsos 55 Conclusions Kronecker graphs have: –All the static properties Heavy tailed degree distributions Small diameter Multinomial eigenvalues and eigenvectors –All the temporal properties Densification Power Law Shrinking/Stabilizing Diameters –We can formally prove these results

56. CMU SCS GATech 08C. Faloutsos 56 Motivation Data mining: ~ find patterns (rules, outliers) Problem#1: How do real graphs look like? Problem#2: How do they evolve? Problem#3: How to generate realistic graphs TOOLS Problem#4: Who is the ‘master-mind’? Problem#5: Track communities over time

57. CMU SCS GATech 08C. Faloutsos 57 Problem#4: MasterMind – ‘CePS’ w/ Hanghang Tong, KDD 2006 htong cs.cmu.edu

58. CMU SCS GATech 08C. Faloutsos 58 Center-Piece Subgraph(Ceps) Given Q query nodes Find Center-piece ( ) App. –Social Networks –Law Inforcement, … Idea: –Proximity -> random walk with restarts

59. CMU SCS GATech 08C. Faloutsos 59 Case Study: AND query R.AgrawalJiawei Han V.VapnikM.Jordan

60. CMU SCS GATech 08C. Faloutsos 60 Case Study: AND query

61. CMU SCS GATech 08C. Faloutsos 61 Case Study: AND query

62. CMU SCS GATech 08C. Faloutsos 62 2_SoftAnd query ML/Statistics databases

63. CMU SCS GATech 08C. Faloutsos 63 Conclusions Q1:How to measure the importance? A1: RWR+K_SoftAnd Q2:How to do it efficiently? A2:Graph Partition (Fast CePS) –~90% quality –150x speedup (ICDM’06, b.p. award)

64. CMU SCS GATech 08C. Faloutsos 64 Outline Problem definition / Motivation Static & dynamic laws; generators Tools: CenterPiece graphs; Tensors Other projects (Virus propagation, e-bay fraud detection) Conclusions

65. CMU SCS GATech 08C. Faloutsos 65 Motivation Data mining: ~ find patterns (rules, outliers) Problem#1: How do real graphs look like? Problem#2: How do they evolve? Problem#3: How to generate realistic graphs TOOLS Problem#4: Who is the ‘master-mind’? Problem#5: Track communities over time

66. CMU SCS GATech 08C. Faloutsos 66 Tensors for time evolving graphs [Jimeng Sun+ KDD’06] [ “, SDM’07] [ CF, Kolda, Sun, SDM’07 tutorial]

67. CMU SCS GATech 08C. Faloutsos 67 Social network analysis Static: find community structures DB A u t h o r s Keywords 1990

68. CMU SCS GATech 08C. Faloutsos 68 Social network analysis Static: find community structures DB A u t h o r s 1990 1991 1992

69. CMU SCS GATech 08C. Faloutsos 69 Social network analysis Static: find community structures Dynamic: monitor community structure evolution; spot abnormal individuals; abnormal time-stamps

70. CMU SCS GATech 08C. Faloutsos 70 DB DM Application 1: Multiway latent semantic indexing (LSI) DB 2004 1990 Michael Stonebraker Query Pattern U keyword authors keyword U authors Projection matrices specify the clusters Core tensors give cluster activation level Philip Yu

71. CMU SCS GATech 08C. Faloutsos 71 Bibliographic data (DBLP) Papers from VLDB and KDD conferences Construct 2nd order tensors with yearly windows with Each tensor: 4584  3741 11 timestamps (years)

72. CMU SCS GATech 08C. Faloutsos 72 Multiway LSI AuthorsKeywordsYear michael carey, michael stonebraker, h. jagadish, hector garcia-molina queri,parallel,optimization,concurr, objectorient 1995 surajit chaudhuri,mitch cherniack,michael stonebraker,ugur etintemel distribut,systems,view,storage,servic,pr ocess,cache 2004 jiawei han,jian pei,philip s. yu, jianyong wang,charu c. aggarwal streams,pattern,support, cluster, index,gener,queri 2004 Two groups are correctly identified: Databases and Data mining People and concepts are drifting over time DM DB

73. CMU SCS GATech 08C. Faloutsos 73 P2: Clusters/data center monitoring Monitor correlations of multiple measurements Automatically flag anomalous behavior Intemon: intelligent monitoring system –Prof. Greg Ganger and PDL –>100 machines in a data center –warsteiner.db.cs.cmu.edu/demo/intemon.jsp

74. CMU SCS GATech 08C. Faloutsos 74 Network forensics Directional network flows A large ISP with 100 POPs, each POP 10Gbps link capacity [Hotnets2004] –450 GB/hour with compression Task: Identify abnormal traffic pattern and find out the cause normal traffic abnormal traffic destination source destination source (with Prof. Hui Zhang and Dr. Yinglian Xie)

75. CMU SCS GATech 08C. Faloutsos 75 Conclusions Tensor-based methods (WTA/DTA/STA): spot patterns and anomalies on time evolving graphs, and on streams (monitoring)

76. CMU SCS GATech 08C. Faloutsos 76 Motivation Data mining: ~ find patterns (rules, outliers) Problem#1: How do real graphs look like? Problem#2: How do they evolve? Problem#3: How to generate realistic graphs TOOLS Problem#4: Who is the ‘master-mind’? Problem#5: Track communities over time

77. CMU SCS GATech 08C. Faloutsos 77 Outline Problem definition / Motivation Static & dynamic laws; generators Tools: CenterPiece graphs; Tensors Other projects (Virus propagation, e-bay fraud detection, blogs) Conclusions

78. CMU SCS GATech 08C. Faloutsos 78 Virus propagation How do viruses/rumors propagate? Blog influence? Will a flu-like virus linger, or will it become extinct soon?

79. CMU SCS GATech 08C. Faloutsos 79 The model: SIS ‘Flu’ like: Susceptible-Infected-Susceptible Virus ‘strength’ s=  /  Infected Healthy NN1 N3 N2 Prob.  Prob. β Prob. 

80. CMU SCS GATech 08C. Faloutsos 80 Epidemic threshold  of a graph: the value of , such that if strength s =  /  <  an epidemic can not happen Thus, given a graph compute its epidemic threshold

81. CMU SCS GATech 08C. Faloutsos 81 Epidemic threshold  What should  depend on? avg. degree? and/or highest degree? and/or variance of degree? and/or third moment of degree? and/or diameter?

82. CMU SCS GATech 08C. Faloutsos 82 Epidemic threshold [Theorem] We have no epidemic, if β/δ <τ = 1/ λ 1,A

83. CMU SCS GATech 08C. Faloutsos 83 Epidemic threshold [Theorem] We have no epidemic, if β/δ <τ = 1/ λ 1,A largest eigenvalue of adj. matrix A attack prob. recovery prob. epidemic threshold Proof: [Wang+03]

84. CMU SCS GATech 08C. Faloutsos 84 Experiments (Oregon)  /  > τ (above threshold)  /  = τ (at the threshold)  /  < τ (below threshold)

85. CMU SCS GATech 08C. Faloutsos 85 Outline Problem definition / Motivation Static & dynamic laws; generators Tools: CenterPiece graphs; Tensors Other projects (Virus propagation, e-bay fraud detection, blogs) Conclusions

86. CMU SCS GATech 08C. Faloutsos 86 E-bay Fraud detection w/ Polo Chau & Shashank Pandit, CMU

87. CMU SCS GATech 08C. Faloutsos 87 E-bay Fraud detection lines: positive feedbacks would you buy from him/her?

88. CMU SCS GATech 08C. Faloutsos 88 E-bay Fraud detection lines: positive feedbacks would you buy from him/her? or him/her?

89. CMU SCS GATech 08C. Faloutsos 89 E-bay Fraud detection - NetProbe

90. CMU SCS GATech 08C. Faloutsos 90 Outline Problem definition / Motivation Static & dynamic laws; generators Tools: CenterPiece graphs; Tensors Other projects (Virus propagation, e-bay fraud detection, blogs) Conclusions

91. CMU SCS GATech 08C. Faloutsos 91 Blog analysis with Mary McGlohon (CMU) Jure Leskovec (CMU) Natalie Glance (now at Google) Mat Hurst (now at MSR) [SDM’07]

92. CMU SCS GATech 08C. Faloutsos 92 Cascades on the Blogosphere B1B1 B2B2 B4B4 B3B3 a b c d e 1 B1B1 B2B2 B4B4 B3B3 1 1 2 3 1 Blogosphere blogs + posts Blog network links among blogs Post network links among posts Q1: popularity-decay of a post? Q2: degree distributions?

93. CMU SCS GATech 08C. Faloutsos 93 Q1: popularity over time Days after post Post popularity drops-off – exponentially? days after post # in links 1 2 3

94. CMU SCS GATech 08C. Faloutsos 94 Q1: popularity over time Days after post Post popularity drops-off – exponentially? POWER LAW! Exponent? # in links (log) 1 2 3 days after post (log)

95. CMU SCS GATech 08C. Faloutsos 95 Q1: popularity over time Days after post Post popularity drops-off – exponentially? POWER LAW! Exponent? -1.6 (close to -1.5: Barabasi’s stack model) # in links (log) 1 2 3 -1.6 days after post (log)

96. CMU SCS GATech 08C. Faloutsos 96 Q2: degree distribution 44,356 nodes, 122,153 edges. Half of blogs belong to largest connected component. blog in-degree count B1B1 B2B2 B4B4 B3B3 1 1 2 3 1 ??

97. CMU SCS GATech 08C. Faloutsos 97 Q2: degree distribution 44,356 nodes, 122,153 edges. Half of blogs belong to largest connected component. blog in-degree count B1B1 B2B2 B4B4 B3B3 1 1 2 3 1

98. CMU SCS GATech 08C. Faloutsos 98 Q2: degree distribution 44,356 nodes, 122,153 edges. Half of blogs belong to largest connected component. blog in-degree count in-degree slope: -1.7 out-degree: -3 ‘rich get richer’

99. CMU SCS GATech 08C. Faloutsos 99 OVERALL CONCLUSIONS Graphs pose a wealth of fascinating problems self-similarity and power laws work, when textbook methods fail! New patterns (shrinking diameter!) New generator: Kronecker SVD / tensors / RWR: valuable tools

100. CMU SCS GATech 08C. Faloutsos 100 Next steps: edges with –weights; and/or –categorical attributes and/or –time-stamps nodes with attributes scalability (hadoop – PetaScale [Bader])

101. CMU SCS GATech 08C. Faloutsos 101 ‘Philosophical’ observations Graph mining brings together: ML/AI / IR; Stat, Num. analysis; Systems (DB (Gb/Tb), Networks ) AND sociology, epidemiology physics (phase transitions, Ising spins, percolation) biology (PPI, regulatory gene networks) business –(blogs; facebook/linkedIn/2ndLife... ) –recommendation systems (NetFlix)

102. CMU SCS GATech 08C. Faloutsos 102 References Hanghang Tong, Christos Faloutsos, and Jia-Yu Pan Fast Random Walk with Restart and Its Applications ICDM 2006, Hong Kong.Fast Random Walk with Restart and Its Applications Hanghang Tong, Christos Faloutsos Center-Piece Subgraphs: Problem Definition and Fast Solutions, KDD 2006, Philadelphia, PACenter-Piece Subgraphs: Problem Definition and Fast Solutions,

103. CMU SCS GATech 08C. Faloutsos 103 References Jure Leskovec, Jon Kleinberg and Christos Faloutsos Graphs over Time: Densification Laws, Shrinking Diameters and Possible Explanations KDD 2005, Chicago, IL. ("Best Research Paper" award).Graphs over Time: Densification Laws, Shrinking Diameters and Possible Explanations Jure Leskovec, Deepayan Chakrabarti, Jon Kleinberg, Christos Faloutsos Realistic, Mathematically Tractable Graph Generation and Evolution, Using Kronecker Multiplication (ECML/PKDD 2005), Porto, Portugal, 2005.Realistic, Mathematically Tractable Graph Generation and Evolution, Using Kronecker MultiplicationECML/PKDD 2005

104. CMU SCS GATech 08C. Faloutsos 104 References Jure Leskovec and Christos Faloutsos, Scalable Modeling of Real Graphs using Kronecker Multiplication, ICML 2007, Corvallis, OR, USA Shashank Pandit, Duen Horng (Polo) Chau, Samuel Wang and Christos Faloutsos NetProbe: A Fast and Scalable System for Fraud Detection in Online Auction Networks WWW 2007, Banff, Alberta, Canada, May 8-12, 2007.NetProbe: A Fast and Scalable System for Fraud Detection in Online Auction Networks Jimeng Sun, Dacheng Tao, Christos Faloutsos Beyond Streams and Graphs: Dynamic Tensor Analysis, KDD 2006, Philadelphia, PA Beyond Streams and Graphs: Dynamic Tensor Analysis,

105. CMU SCS GATech 08C. Faloutsos 105 References Jimeng Sun, Yinglian Xie, Hui Zhang, Christos Faloutsos. Less is More: Compact Matrix Decomposition for Large Sparse Graphs, SDM, Minneapolis, Minnesota, Apr 2007. [pdf]pdf

106. CMU SCS GATech 08C. Faloutsos 106 Contact info: www. cs.cmu.edu /~christos (w/ papers, datasets, code, etc)

107. CMU SCS GATech 08C. Faloutsos 107

108. CMU SCS GATech 08C. Faloutsos 108 Promising directions Reaching out –Sociology, epidemiology; physics, ++… –Computer networks, security, intrusion det. –Num. analysis (tensors) time IP-source IP-destination

109. CMU SCS GATech 08C. Faloutsos 109 Promising directions – cont’d Scaling up, to Gb/Tb/Pb –Storage Systems –Parallelism (hadoop/map-reduce)

110. CMU SCS GATech 08C. Faloutsos 110 E.g.: self-* system @ CMU >200 nodes 40 racks of computing equipment 774kw of power. target: 1 PetaByte goal: self-correcting, self- securing, self-monitoring, self-...