Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:Knowledge-guided Representation Learning
Speaker:Achim Rettinger
coming from:KIT Karlsruhe
Speakers Bio:
Event Type:Talk
Visibility:D1, D2, D3, D4, D5, RG1, SWS, MMCI
We use this to send out email in the morning.
Level:Public Audience
Language:English
Date, Time and Location
Date:Monday, 11 June 2018
Time:08:00
Duration:60 Minutes
Location:Saarbr├╝cken
Building:E1 5
Room:029
Abstract
Representation learning is crucial to the recent success of deep learning. While it is typically associated with learning of more abstract representations from raw sensory inputs, there has been growing interest in how symbolic knowledge can be captured as well. Specifically, the availability of large-scale knowledge graphs has opened up new opportunities for machine learning applications. The state-of-the-art neural network models for knowledge graph embeddings build on a large body of previous work on graphical models, graph kernels and tensor methods which all extract latent representation from knowledge graphs. The baseline optimization criteria has since been the prediction of unknown links in the graph.

The dense vector representations obtained by knowledge graph embedding techniques provide three fundamental advantages: First, they enable the integration of information from different modalities like images and multilingual text with symbolic knowledge into one common representation. Such cross-modal embeddings provide measurable benefits for semantic similarity benchmarks and entity-type prediction tasks. Second, they allow to transfer knowledge across modalities even for concepts that are not represented in the other modalities.
Third, they are key to solving complex AI tasks beyond link prediction, like image
captioning or multi-step decision making. Again, the transfer of information from other modalities can be beneficial. E.g., cross-modal knowledge transfer assist the captioning of images which contain visual objects that are unseen in the image-caption parallel training data. Ultimately, this allows to tackle several real-world application areas where knowledge-guided representation learning can provide considerable benefits, like media analytics, manufacturing or medical engineering.

Contact
Name(s):Connie Balzert
Video Broadcast
Video Broadcast:NoTo Location:
Tags, Category, Keywords and additional notes
Note:
Attachments, File(s):

Created:
Connie Balzert/MPI-INF, 06/08/2018 11:44 AM
Last modified:
Uwe Brahm/MPII/DE, 06/11/2018 07:01 AM
  • Connie Balzert, 06/08/2018 11:44 AM -- Created document.