Private:progress-gao - Revision history

Feig at 08:01, 16 November 2011

2011-11-16T08:01:11Z

2011-11-16T08:00:51Z

2011-11-16T06:09:26Z

2011-10-18T08:43:18Z

2011-10-18T08:42:27Z

2011-10-05T05:56:34Z

2011-09-21T03:19:09Z

2011-06-01T02:31:12Z

2011-06-01T02:25:34Z

2011-05-17T03:43:15Z

@@ Line 3: / Line 3: @@
 **None.
-=== Nov 10th ===
+=== Nov 16th ===
 * Leveraged Amazon Elastic MapReduce cluster to run the proposed method on Wikipedia dataset, and got great reduction of computing time when comparing with that using 5-node cluster.
 * Run the proposed method, Parallel Spectral Clustering and Spectral Clustering on Wikipedia datasets. The results show that the proposed method has better performance than the other two methods.

@@ Line 5: / Line 5: @@
 === Nov 10th ===
 * Leveraged Amazon Elastic MapReduce cluster to run the proposed method on Wikipedia dataset, and got great reduction of computing time when comparing with that using 5-node cluster.
-* Run the proposed method, distributed Spectral Clustering and Spectral Clustering on Wikipedia datasets. The results show that the proposed method has better performance than the other two methods.
+* Run the proposed method, Parallel Spectral Clustering and Spectral Clustering on Wikipedia datasets. The results show that the proposed method has better performance than the other two methods.
 === Oct 17th ===

@@ Line 2: / Line 2: @@
 * Courses:
 **None.
 === Oct 17th ===

@@ Line 6: / Line 6: @@
 * '''Report:''' [https://cs-nsl-svn.cs.surrey.sfu.ca/cssvn/nsl-members/gao/reports/Report_Oct_17th/reportTemplate.pdf here]
 * Experimented with the tuning of the parameter "how many terms to keep"
-* Run large dataset on the proposed algorithm with good performance.
+* Run large dataset on the proposed algorithm with good performance (91.38%).
 === Oct 4th ===

@@ Line 2: / Line 2: @@
 * Courses:
 **None.
 === Oct 4th ===

← Older revision		Revision as of 03:19, 21 September 2011
Line 1:		Line 1:
		+	= Fall 2011 (RA) =
		+	* Courses:
		+	**None.
		+
		+	=== Sep 20th ===
		+	* '''Report:''' [https://cs-nsl-svn.cs.surrey.sfu.ca/cssvn/nsl-members/gao/reports/Report_Sep_20th/reportTemplate.pdf here]
		+	* Successfully crawled 3,550,567 web pages from Wikipedia, forming 739,144 categories.
		+	* Processed the raw HTML files and have it ready for test purpose.
		+	* Now working on stop-word removing and stemming.
		+	* In the following 4-5 days, will have the dataset fully processed and ready.
		+	* And then, one day to do tf-idf on the dataset (since that part of the code is done).
		+	* Following that, first test the dataset on kmeans; and then, try spectral clustering on the data.
		+
	= Summer 2011 (RA) =		= Summer 2011 (RA) =
	* Courses:		* Courses:

@@ Line 6: / Line 6: @@
 * '''Report:''' [https://cs-nsl-svn.cs.surrey.sfu.ca/cssvn/nsl-members/gao/reports/Report_May_30th/reportTemplate.pdf here]
 * Added Nyström method into the comparison of proposed method and PSC method, in the aspect of accuracy.
-* Continued to run the experiment on large dataset.
+* Continued to run the experiment on large dataset. Will continue the experiment and collect more data.
 * Analysed the experiment results in the experiment result part.
 * Included more sources to show the legitimacy of the evaluation metrics.

@@ Line 2: / Line 2: @@
 * Courses:
 **None.
 === May 16th ===
 * Got Parallel SC method (using MPICH2 in implementation) running on NSL cluster and got the result for comparison purpose. The hardware platform remains unchanged (NSL cluster).
 * Examined and ran a few experiments with Nystrom Extension Spectral Clustering method (in matlab) and "Fast approximate spectral clustering" method (in R). However, the problem here is that these two method runs on single machine, which will somehow defeat the comparison purpose (because platform is changed). Moreover, the memory usage limitation of Matlab will fail the experiment when using 2^12 data set.