International Database Conference

SIGMOD(Special Interest Group on Management Of Data): 97 points, the highest meeting of databases, once a year, involving a wide range of applications (because theoretical articles include PODS (Symposium on Principles of Database Systems ). I didn't say that. Jing Yang is like Qingjiang. This meeting is not only a double-blind review, but also a rebuttal procedure, which is unique and distinctive.

URL: http://www.sigmod.org/

 

VLDB(Very Large Data Base): 95 points, very good database meetings, once a year. Similar to SIGMOD, it has a wide range of applications.

URL: http://www.vldb.org/

 

Comparison between SIGMOD and VLDB:

1. From the quality of the article, SIGMOD and VLDB are difficult to distinguish, and no one is better than anyone else. Their scope is almost the same. Many cool people believe that this year's rebuttal procedure was not very successful. It is difficult to make every article fair and equitable because there are too many submissions. A lot of rebuttal is not visible.

2. double-blind is a double-edged sword. Over the past few years, some people have contributed documents in the style of impersonating a cool man. On the contrary, the quality of VLDB reviews has been high. Every year, VLDB has a very theoretical paper.

3. In general, I think SIGMOD is better. According to my personal articles, I also feel this way. However, this is not important. The difference is also true.

 

PODS(Symposium on Principles of Database Systems): 95 points. It is the "best meeting on database theory and a good theoretical meeting ". Co-located with sigmod is always used every year. People with algorithm backgrounds (you can count the number of people with pods articles from motwani group) and some people with AI backgrounds (after all, sigart (Special Interest Group on Artificial Intelligence) is also one of the sponsors ). It has far less influence than sigmod, but the quality of the article is relatively neat, and variance is less than sigmod (and any other database Conference ). "Pods never had a really bad paper," said one cow.

 

KDD(Knowledge Discovery and Data Mining): Full paper 95 points, poster/short paper 90 points. The highest meeting for data mining. Due to the lack of historical accumulation and small field circles, KDD is inferior to sigmod at present. I think we can use this analogy: KDD: sigmod = crypto: stoc (Symposium on Theory of computing ). Looking back at the history of cryptography, the best article is generally published in stoc/focs rather than crypto/eurocrypt. How similar is Data Mining today! However, if you look at today's cryptographic articles, there are already top-level cryptographic experts (so I cannot write a name) who no longer contribute to stoc/focs. I think the same thing will happen in Data Mining in the near future. Let's wait and see.

URL: http://www.sigkdd.org/

 

In the past few years, KDD has a high quality. Its full paper quality is higher than sigmod/vldb's paper quality in data mining. The reason is that there are very few data mining personnel in sigmod/vldb reviewers, and the review criteria may not be well grasped. Several pieces of sigmod/vldb Data Mining paper have follow some KDD paper over the past few years. In KDD, it is really difficult to get a full paper. Fudan took an article last year, which is very valuable. This year, they took another sigmod demo, indicating that the work was indeed solid.

 

I have heard that in many places, if you have a sigmod, vldb, or KDD, you will be able to graduate from a doctor. If you have two articles, you will find a good job. "The revolution has not yet succeeded. comrades still need to work hard !"

 

ICDE(International Conference on Data Engineering): 92 points. A good Database Conference is also a hodgedge. The advantage is wide coverage and high inclusiveness. The disadvantage is that the level of the article is uneven.

URL: http://www.icde.org/

 

EDBT(Extending Database Technology): 88 points. A good database meeting was held every several years. The recording rate was very low. However, the historical accumulation was insufficient, and the impact was far lower than that of icde.

 

ICDT (International Conference on database theory): 88 points, European version of pods, Second Meeting on database theory.

Http://www.informatik.uni-trier.de /~ Ley/DB/CONF/ICDT/

Http://www.math.spbu.ru/edbticdt/index.html ----- DBT/ICDT 2009 Joint Conference two Conference 2009 held together in Russia

 

Like sigmod/vldb, icde and edbt are comparable in quality and impact. Other problems, such as cikm, ICDM, SDM, ssdbm, and pkdd, are worse than the preceding ones.

 

Cikm (Conference on Information and Knowledge Management): 85 points.

 

SDM: full paper 90 points, poster/short paper 85 points. SIAM (http://www.siam.org/) data mining conference, and ICDM and listed as the second in the field of data mining, there is a significant gap than KDD. It seems that there are many people with statistical backgrounds, and some people with machine learning backgrounds are compared with diversified.

 

ICDM (International Conference on Data Mining): full paper 90 points, poster/short paper 85 points. IEEE Data Mining Conference, which is the second place in the field of data mining with SDM, is significantly different from KDD.

Reference: http://www.cs.uvm.edu /~ Icdm/

 

PKDD (Practice of Knowledge Discovery in Databases): 83 points (because the number of poster/short papers is small, it is not distinguished ). It seems to be the European version of KDD, but it is very different from KDD.

Reference: http://www.ecmlpkdd2008.org/

 

ACM(Association for Computing Machinery)SIGMOD, VLDB, PODS, KDD); IEEE (Institute of Electrical and Electronics Engineers)Its database Conference (ICDE), ICDM).