Re: the slides for my talk @ FOSDEM

2012-02-07 Thread Claudio Martella
Hi Sebastian,

thanks for your feedback on the slides.

As a matter of fact I'm aware of the pegasus matrix-based optimization
as of the shimmy technique by Jimmy Lin. I thought that this kind of
technique is general enough for all iterative graph algorithms, not
just PR, and mostly using the naive algorithm would just help me out
explaining the presentation. Messaging the adjacent vertices from the
Mapper by iterating over them and emitting (otherVertex, myPartialPR)
maps easily to our messaging paradigm. I'll maybe make it more clear
in the next presentation.

Thanks!


On Mon, Feb 6, 2012 at 2:54 PM, Sebastian Schelter s...@apache.org wrote:
 Hi Claudio,

 nice job with the slides! I have only one small point to criticize:

 When PageRank is implemented with MapReduce, it's not necessary to have
 the graph passed through in each iteration. Mahout for example uses
 power iterations where the adjacency matrix is multiplied by the
 pagerank vector and only that vector has to be sent over the network.
 Pegasus uses a similar approach.

 /s



 On 06.02.2012 12:24, Claudio Martella wrote:
 Hello guys,

 for those interested, here are the slides for my talk at FOSDEM.

 http://prezi.com/9ake_klzwrga/apache-giraph-distributed-graph-processing-in-the-cloud/

 The event was very nice, a tight community and a great interest in
 Giraph. Isabel Drost, one of the organizers of Berlin Buzzwords,
 invited the talk there. Jakob, are you still planning to talk there?
 Maybe we can split Kafka/Giraph talks?

 Best,
 Claudio





-- 
   Claudio Martella
   claudio.marte...@gmail.com


Re: the slides for my talk @ FOSDEM

2012-02-06 Thread Sebastian Schelter
Hi Claudio,

nice job with the slides! I have only one small point to criticize:

When PageRank is implemented with MapReduce, it's not necessary to have
the graph passed through in each iteration. Mahout for example uses
power iterations where the adjacency matrix is multiplied by the
pagerank vector and only that vector has to be sent over the network.
Pegasus uses a similar approach.

/s



On 06.02.2012 12:24, Claudio Martella wrote:
 Hello guys,
 
 for those interested, here are the slides for my talk at FOSDEM.
 
 http://prezi.com/9ake_klzwrga/apache-giraph-distributed-graph-processing-in-the-cloud/
 
 The event was very nice, a tight community and a great interest in
 Giraph. Isabel Drost, one of the organizers of Berlin Buzzwords,
 invited the talk there. Jakob, are you still planning to talk there?
 Maybe we can split Kafka/Giraph talks?
 
 Best,
 Claudio
 



Re: the slides for my talk @ FOSDEM

2012-02-06 Thread Jakob Homan
 Jakob, are you still planning to talk there? Maybe we can split Kafka/Giraph 
 talks?
Yes, I've already submitted my Giraph talk.  I'm not really involved
with Kafka at the moment; if I go, it'll be on the Giraph talk...


On Mon, Feb 6, 2012 at 5:54 AM, Sebastian Schelter s...@apache.org wrote:
 Hi Claudio,

 nice job with the slides! I have only one small point to criticize:

 When PageRank is implemented with MapReduce, it's not necessary to have
 the graph passed through in each iteration. Mahout for example uses
 power iterations where the adjacency matrix is multiplied by the
 pagerank vector and only that vector has to be sent over the network.
 Pegasus uses a similar approach.

 /s



 On 06.02.2012 12:24, Claudio Martella wrote:
 Hello guys,

 for those interested, here are the slides for my talk at FOSDEM.

 http://prezi.com/9ake_klzwrga/apache-giraph-distributed-graph-processing-in-the-cloud/

 The event was very nice, a tight community and a great interest in
 Giraph. Isabel Drost, one of the organizers of Berlin Buzzwords,
 invited the talk there. Jakob, are you still planning to talk there?
 Maybe we can split Kafka/Giraph talks?

 Best,
 Claudio




Re: the slides for my talk @ FOSDEM

2012-02-06 Thread Claudio Martella
Ok weird, i asked and she mentioned she hasn't received any. Good luck.

On Monday, February 6, 2012, Jakob Homan jgho...@gmail.com wrote:
 Jakob, are you still planning to talk there? Maybe we can split
Kafka/Giraph talks?
 Yes, I've already submitted my Giraph talk.  I'm not really involved
 with Kafka at the moment; if I go, it'll be on the Giraph talk...


 On Mon, Feb 6, 2012 at 5:54 AM, Sebastian Schelter s...@apache.org wrote:
 Hi Claudio,

 nice job with the slides! I have only one small point to criticize:

 When PageRank is implemented with MapReduce, it's not necessary to have
 the graph passed through in each iteration. Mahout for example uses
 power iterations where the adjacency matrix is multiplied by the
 pagerank vector and only that vector has to be sent over the network.
 Pegasus uses a similar approach.

 /s



 On 06.02.2012 12:24, Claudio Martella wrote:
 Hello guys,

 for those interested, here are the slides for my talk at FOSDEM.


http://prezi.com/9ake_klzwrga/apache-giraph-distributed-graph-processing-in-the-cloud/

 The event was very nice, a tight community and a great interest in
 Giraph. Isabel Drost, one of the organizers of Berlin Buzzwords,
 invited the talk there. Jakob, are you still planning to talk there?
 Maybe we can split Kafka/Giraph talks?

 Best,
 Claudio




-- 
   Claudio Martella
   claudio.marte...@gmail.com


Re: the slides for my talk @ FOSDEM

2012-02-06 Thread Jakob Homan
Also, Claudio, don't forget to add your presentation to the website:
https://incubator.apache.org/giraph/

On Mon, Feb 6, 2012 at 7:53 AM, Jakob Homan jgho...@gmail.com wrote:
 Jakob, are you still planning to talk there? Maybe we can split Kafka/Giraph 
 talks?
 Yes, I've already submitted my Giraph talk.  I'm not really involved
 with Kafka at the moment; if I go, it'll be on the Giraph talk...


 On Mon, Feb 6, 2012 at 5:54 AM, Sebastian Schelter s...@apache.org wrote:
 Hi Claudio,

 nice job with the slides! I have only one small point to criticize:

 When PageRank is implemented with MapReduce, it's not necessary to have
 the graph passed through in each iteration. Mahout for example uses
 power iterations where the adjacency matrix is multiplied by the
 pagerank vector and only that vector has to be sent over the network.
 Pegasus uses a similar approach.

 /s



 On 06.02.2012 12:24, Claudio Martella wrote:
 Hello guys,

 for those interested, here are the slides for my talk at FOSDEM.

 http://prezi.com/9ake_klzwrga/apache-giraph-distributed-graph-processing-in-the-cloud/

 The event was very nice, a tight community and a great interest in
 Giraph. Isabel Drost, one of the organizers of Berlin Buzzwords,
 invited the talk there. Jakob, are you still planning to talk there?
 Maybe we can split Kafka/Giraph talks?

 Best,
 Claudio




Re: the slides for my talk @ FOSDEM

2012-02-06 Thread Claudio Martella
Sure, I ll wait until the video is put on YouTube and put both.

On Monday, February 6, 2012, Jakob Homan jgho...@gmail.com wrote:
 Also, Claudio, don't forget to add your presentation to the website:
 https://incubator.apache.org/giraph/

 On Mon, Feb 6, 2012 at 7:53 AM, Jakob Homan jgho...@gmail.com wrote:
 Jakob, are you still planning to talk there? Maybe we can split
Kafka/Giraph talks?
 Yes, I've already submitted my Giraph talk.  I'm not really involved
 with Kafka at the moment; if I go, it'll be on the Giraph talk...


 On Mon, Feb 6, 2012 at 5:54 AM, Sebastian Schelter s...@apache.org
wrote:
 Hi Claudio,

 nice job with the slides! I have only one small point to criticize:

 When PageRank is implemented with MapReduce, it's not necessary to have
 the graph passed through in each iteration. Mahout for example uses
 power iterations where the adjacency matrix is multiplied by the
 pagerank vector and only that vector has to be sent over the network.
 Pegasus uses a similar approach.

 /s



 On 06.02.2012 12:24, Claudio Martella wrote:
 Hello guys,

 for those interested, here are the slides for my talk at FOSDEM.


http://prezi.com/9ake_klzwrga/apache-giraph-distributed-graph-processing-in-the-cloud/

 The event was very nice, a tight community and a great interest in
 Giraph. Isabel Drost, one of the organizers of Berlin Buzzwords,
 invited the talk there. Jakob, are you still planning to talk there?
 Maybe we can split Kafka/Giraph talks?

 Best,
 Claudio




-- 
   Claudio Martella
   claudio.marte...@gmail.com


Re: the slides for my talk @ FOSDEM

2012-02-06 Thread André Kelpe
2012/2/6 Claudio Martella claudio.marte...@gmail.com:
 Hello guys,

 for those interested, here are the slides for my talk at FOSDEM.

 http://prezi.com/9ake_klzwrga/apache-giraph-distributed-graph-processing-in-the-cloud/

Nice slide-deck, to bad I was to late at fosdem yesterday to see it...
Question: Is the official giraph logo? I was looking for one, that I
want to include in an internal slide deck and could not find one.

Thanks!

André