Recent Advances and Trends in Large-Scale Kernel Methods

Kashima, Hisashi; Idé, Tsuyoshi; Kato, Tsuyoshi; Sugiyama, Masashi

doi:10.1587/transinf.e92.d.1338

Cited by 19 publications

(5 citation statements)

References 64 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[25]. Therefore WNN-GIP is more efficient than KBMF2K, since the total time complexity of each iteration in the variational approximation method used in KBMF2K is , where is the subspace dimensionality used in the method.…”

Section: Discussionmentioning

confidence: 99%

Predicting Drug-Target Interactions for New Drug Compounds Using a Weighted Nearest Neighbor Profile

2013

View full text Add to dashboard Cite

In silico discovery of interactions between drug compounds and target proteins is of core importance for improving the efficiency of the laborious and costly experimental determination of drug-target interaction. Drug-target interaction data are available for many classes of pharmaceutically useful target proteins including enzymes, ion channels, GPCRs and nuclear receptors. However, current drug-target interaction databases contain a small number of drug-target pairs which are experimentally validated interactions. In particular, for some drug compounds (or targets) there is no available interaction. This motivates the need for developing methods that predict interacting pairs with high accuracy also for these 'new' drug compounds (or targets). We show that a simple weighted nearest neighbor procedure is highly effective for this task. We integrate this procedure into a recent machine learning method for drug-target interaction we developed in previous work. Results of experiments indicate that the resulting method predicts true interactions with high accuracy also for new drug compounds and achieves results comparable or better than those of recent state-of-the-art algorithms. Software is publicly available at http://cs.ru.nl/~tvanlaarhoven/drugtarget2013/.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting Drug-Target Interactions for New Drug Compounds Using a Weighted Nearest Neighbor Profile

2013

View full text Add to dashboard Cite

show abstract

“…So, to make a RLS prediction using the Kronecker product kernel we only need to perform the two eigendecompositions and some matrix multiplications, bringing the runtime down to O(n d 3 + nt 3 ). The efficiency of this computation could be further improved yielding a quadratic computational complexity by applying recent techniques for large scale kernel methods for computing the two kernel decompositions (Kashima et al, 2009b;Wu et al, 2006).…”

Section: Rls-kron Classifiermentioning

confidence: 99%

Gaussian interaction profile kernels for predicting drug–target interaction

2011

View full text Add to dashboard Cite

show abstract

“…[21]). And in the future, we will consider the issue of speeding up decoding with structured models [28], [32], [45].…”

Section: Discussionmentioning

confidence: 99%

“…We will combine our method with other techniques that provide sparse solutions, for example, kernel methods on a budget (Dekel and Singer, 2007;Dekel et al, 2008;Orabona et al, 2008) or kernel approximation (surveyed in Kashima et al (2009)). It is also easy to combine our method with SVMs with partial kernel expansion (Goldberg and Elhadad, 2008), which will yield slower but more space-efficient classifiers.…”

Section: Discussionmentioning

confidence: 99%

Efficient Classification with Conjunctive Features

Yoshinaga

2012

Journal of Information Processing

View full text Add to dashboard Cite

This paper proposes a method that speeds up a classifier trained with many conjunctive features: combinations of (primitive) features. The key idea is to precompute as partial results the weights of primitive feature vectors that represent fundamental classification problems and appear frequently in the target task. A prefix tree (trie) compactly stores the primitive feature vectors with their weights, and it enables the classifier to find for a given feature vector its longest prefix feature vector whose weight has already been computed. Experimental results on base phrase chunking and dependency parsing demonstrated that our method speeded up the svm and llm classifiers by a factor of 1.8 to 10.6.

show abstract

Recent Advances and Trends in Large-Scale Kernel Methods

Cited by 19 publications

References 64 publications

Predicting Drug-Target Interactions for New Drug Compounds Using a Weighted Nearest Neighbor Profile

Predicting Drug-Target Interactions for New Drug Compounds Using a Weighted Nearest Neighbor Profile

Gaussian interaction profile kernels for predicting drug–target interaction

Efficient Classification with Conjunctive Features

Contact Info

Product

Resources

About