Local Probabilistic Models for Link Prediction
- ISSN: 15504786
- ISBN: 0769530184
- DOI: 10.1109/ICDM.2007.108
Abstract
One of the core tasks in social network analysis is to predict the formation of links (i.e. various types of relationships) over time. Previous research has generally represented the social network in the form of a graph and has leveraged topological and semantic measures of similarity between two nodes to evaluate the probability of link formation. Here we introduce a novel local probabilistic graphical model method that can scale to large graphs to estimate the joint co-occurrence probability of two nodes. Such a probability measure captures information that is not captured by either topological measures or measures of semantic similarity, which are the dominant measures used for link prediction. We demonstrate the effectiveness of the co-occurrence probability feature by using it both in isolation and in combination with other topological and semantic features for predicting co-authorship collaborations on real datasets.
Local Probabilistic Models for Link Prediction
Jean-Francois Paiement a;, Samy Bengio b, Douglas Eck c
aIdiap Research Institute, Centre du Parc, Rue Marconi 19, Case Postale 592,
CH-1920 Martigny, Switzerland
bGoogle, 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA
cUniversity of Montreal, Department of Computer Science and Operations
Research, Pavillon Andre-Aisenstadt, CP 6128, succ Centre-Ville, Montreal, QC,
H3C 3J7, Canada
Abstract
Chord progressions are the building blocks from which tonal music is constructed.
The choice of a particular representation for chords has a strong impact on statis-
tical modeling of the dependence between chord symbols and the actual sequences
of notes in polyphonic music. Melodic prediction is used in this paper as a bench-
mark task to evaluate the quality of four chord representations using two prob-
abilistic model architectures derived from Input/Output Hidden Markov Models
(IOHMMs). Likelihoods and conditional and unconditional prediction error rates
are used as complementary measures of the quality of each of the proposed chord
representations. We observe empirically that di erent chord representations are op-
timal depending on the chosen evaluation metric. Also, representing chords only by
their roots appears to be a good compromise in most of the reported experiments.
Key words: Music Models, Graphical Models, Probabilistic Algorithms, Machine
Learning.
1 Introduction
Probabilistic models for analysis and generation of polyphonic music would be
useful in a broad range of applications, from contextual music generation to on-
line music recommendation and retrieval. However, modeling music involves
Corresponding author.
Email addresses: paiement@gmail.com (Jean-Francois Paiement),
bengio@google.com (Samy Bengio), douglas.eck@umontreal.ca (Douglas Eck).
Preprint submitted to Arti cial Intelligence 4 June 2009
Sign up today - FREE
Mendeley saves you time finding and organizing research. Learn more
- All your research in one place
- Add and import papers easily
- Access it anywhere, anytime
