[Syscussion] upcoming syscussion: struc2vec: Learning Node Representations from Structural Identity

[Tasos Bakogiannis]

Καλησπέρα,


την Παρασκευή 2/3/18 θα παρουσιαστεί το παρακάτω paper:


Title:
struc2vec: Learning Node Representations from Structural Identity


Authors:
Leonardo F. R. Ribeiro, Pedro H. P. Saverese, Daniel R. Figueiredo


Abstract:
Structural identity is a concept of symmetry in which network
nodes are identified according to the network structure and their
relationship to other nodes. Structural identity has been studied
in theory and practice over the past decades, but only recently
has it been addressed with representational learning techniques.
This work presents struc2vec, a novel and flexible framework for
learning latent representations for the structural identity of nodes.
struc2vec uses a hierarchy to measure node similarity at differ-
ent scales, and constructs a multilayer graph to encode structural
similarities and generate structural context for nodes. Numerical
experiments indicate that state-of-the-art techniques for learning
node representations fail in capturing stronger notions of structural
identity, while struc2vec exhibits much superior performance in
this task, as it overcomes limitations of prior approaches. As a con-
sequence, numerical experiments indicate that struc2vec improves
performance on classification tasks that depend more on structural
identity.


Link:
http://www.kdd.org/kdd2017/papers/view/struc2vec-learning-node-representations-from-structural-identity


Τάσος.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 473 bytes
Desc: OpenPGP digital signature
URL: <http://lists.cslab.ece.ntua.gr/pipermail/syscussion/attachments/20180227/535438b3/attachment.pgp>