KDD Best Papers CollectingKDD's mission to provide the premier forum for advancement, education, and adoption of the "science" of knowledge discovery and data mining from all types of data stored in computers and networks of computers.
knowledge discovery and data mining, (2019)
This paper introduced SPADL, a language for representing event stream data that is designed with the goal of facilitating data analysis, and VAEP, a framework for assigning a value to each individual player action during a soccer game
Cited by25BibtexViews86Links
0
0
pp.2145-2155 (2019)
We demonstrated the utility of using device-derived features to detect cognitive impairment in the small cohort of 31 symptomatics and 82 healthy controls included in the analysis, presenting a model achieving Area Under the ROC Curve=0.80 using device-derived features and demogr...
Cited by9BibtexViews49Links
0
0
We introduce a new direct nested dissection method for local density of states, as well as new graph-specific modifications to improve the convergence of the Kernel Polynomial Method and Gauss Quadrature and Lanczos approaches
Cited by7BibtexViews50Links
0
0
pp.1205-1215 (2019)
Based on this influence model, we studied the Impression Counts for Outdoor Advertising problem and proved that it is NP-hard to approximate
Cited by5BibtexViews47Links
0
0
international joint conference on artificial intelligence, (2018): 2847-2856
We presented the first work on adversarial attacks to graphs, focusing on the task of node classification via graph convolutional networks
Cited by137BibtexViews412Links
0
0
Tom Hope, Joel Chan, Aniket Kittur, Dafna Shahaf
IJCAI, pp.5274-5278, (2018)
We explored the potential of learning and leveraging a weak structural representation for product descriptions
Cited by20BibtexViews99Links
0
0
We propose FRAUDAR, a fraud detection algorithm which provably bounds the amount of fraud adversaries can have, even in face of camouflage
Cited by129BibtexViews172Links
0
0
ACM Knowledge Discovery and Data Mining, (2015)
Our model abstracts the privacy aspects in the link structure of the social network and establishes a formal framework to study e cient social network algorithms that respect the privacy of the links; such algorithms operate, for a given user, on this user’s private graph and on ...
Cited by28BibtexViews75Links
0
0
KDD, pp.891-900, (2014)
We evaluate the algorithms based on two metrics: the amount of time elapsed for one Gibbs sampling iteration and perplexity
Cited by187BibtexViews212Links
0
0
knowledge discovery and data mining, (2013): 581-588
Low rank approximations for such matrices are used in common data mining tasks such as Principal Component Analysis, Latent Semantic Indexing, and k-means clustering
Cited by197BibtexViews86Links
0
0
KDD, (2012): 262-270
While our work has focused on fast sequential search, we believe that for Dynamic Time Warping, our work is faster than all known indexing efforts
Cited by753BibtexViews211Links
0
0
ACM Transactions on Knowledge Discovery From Data, no. 4 (2012): ArticleNo.23-ArticleNo.23
7 Conclusions In summary, we introduce a block minimization framework for solving large linear classification problems when data cannot fit in memory
Cited by182BibtexViews129Links
0
0
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence ..., pp.2734-2739, (2011)
Our goal is to help people fight information overload by providing a structured, easy way to navigate between topics
Cited by219BibtexViews75Links
0
0
ACM Transactions on Knowledge Discovery from Data (TKDD) - Special Issue on the Best of SIGKDD 2011, no. 4 (2011): ArticleNo.15-ArticleNo.15
A rich set of examples from diverse data mining domains given throughout this paper add to our own experience to suggest that in the absence of methodology for handling it, leakage could be the cause of many failures of data mining applications
Cited by92BibtexViews87Links
0
0
Communications of The ACM, no. 4 (2009): 89-97
In an item-item neighborhood model, we showed how the more fundamental relations among items can be revealed by learning how influence between two items rated by a user decays over time. In both factorization and neighborhood models, the inclusion of temporal dynamics proved very...
Cited by1820BibtexViews108Links
0
0
KDD, pp.821-829, (2008)
In this paper we present an efficient algorithm, FastANOVA, for genome-wide two-locus ANOVA test
Cited by52BibtexViews64Links
0
0
KDD, pp.26-35, (2007)
The current work focuses on predictive discrete latent factors based on generalized linear models, in principle, the proposed methodology could apply to non-linear predictive models where the mean is modeled using non-parametric methods like generalized additive models, splines, ...
Cited by86BibtexViews47Links
0
0
KDD, pp.217-226, (2006)
We presented a simple Cutting-Plane Algorithm for training linear Support Vector Machines that is shown to converge in time O for classification and O(sn log(n)) for ordinal regression
Cited by1996BibtexViews431Links
0
0
KDD, pp.177-187, (2005)
The Densification Power Law: In contrast to the standard modeling assumption that the average out-degree remains constant over time, we discover that real graphs have out-degrees that grow over time, following a natural pattern )
Cited by2464BibtexViews227Links
0
0
KDD, pp.59-68, (2004)
The framework can be used with a number of distortion measures, including Bregman divergences and directional measures, and it accommodates trainable measures that can be adapted to specific datasets
Cited by1007BibtexViews93Links
0
0
Keywords
Data MiningData Mining ProblemEuclidean DistanceLarge DatasetsLower BoundSocial NetworkAlgorithms Use Similarity SearchAlias MethodAnalysis FrameworkAnova Test
Authors
Christos Faloutsos
Paper 2
Pedro M. Domingos
Paper 2
Jon M. Kleinberg
Paper 2
Jan Van Haaren
Paper 1
Darya Chudova
Paper 1
Deepak Agarwal
Paper 1
Edo Liberty
Paper 1
Jesin Zakaria
Paper 1
Gustavo Batista
Paper 1
David Bindel
Paper 1