Mapping and Revising Markov Logic Networks for Transfer Learning

By Lilyana Mihalkova, Tuyen N. Huynh, Raymond J. Mooney. 2007

352 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Taskonomy: Disentangling Task Transfer Learning (2018, background): “compositional modeling [33, 8, 11, 21, 53, 89, 87], homomorphic cryptography [40], lifelong learning [90, 13, 82, 81], functional maps [68], certain aspects of Bayesian inference and Dirichlet processes [52, 88, 87, 86, 35, 37], few-shot learning [78, 23, 22, 67, 83], transfer learning [72, 81, 27, ”
Which Tasks Should Be Learned Together in Multi-task Learning? (2019, background): “Transfer learning, [34, 16, 40, 15, 25, 28, 21, 35, 31], is similar to multi-task learning in that solutions are learned for multiple tasks.”
TODTLER: Two-Order-Deep Transfer Learning (2015, methodology): “Conceptually, the closest transfer learning approaches to TODTLER are DTM (Davis and Domingos 2009) and TAMAR (Mihalkova, Huynh, and Mooney 2007), which both perform deep transfer in the context of Markov logic networks.”
Transfer Learning for Activity Recognition: A Survey (2013, unknown): “See [17, 41, 42, 43] for examples of relational-knowledge transfer.”
Transfer Learning using Kolmogorov Complexity: Basic Theory and Empirical Evaluations (2007, background): “To the best of our knowledge, the first paper to address this was[13], and recent works include [17] and[18].”
A Survey on Transfer Learning (2010, background): “Finally, the last case can be referred to as the relationalknowledge-transfer problem [50], which deals with transfer learning for relational domains.”
A Decade Survey of Transfer Learning (2010–2020) (2020, background): “Some studies [80]–[82] have proposed to use Markov Logic Networks.”
Transfer Learning by Mapping with Minimal Target Data (2008, methodology): “We compared SR2LR to MTAMAR on the three domains we used previously ( Mihalkova, Huynh, & Mooney 2007 ): IMDB, UW-CSE, and WebKb,2 treating each possible ordered pair of them as a source and a target.”
Heterogeneous Transfer Learning for Image Classification (2011, unknown): “Recently, transfer learning methods have been proposed to use knowledge from auxiliary data in a different but re-lated domain to help learn the target tasks (Wu and Diet-terich 2004; Mihalkova et al. 2007; Quattoni et al. 2008; Daum´e 2007).”
Flexible Transfer Learning under Support and Model Shift (2014, methodology): “Traditional methods for transfer learning use Markov logic networks [4], parameter learning [5, 6], and Bayesian Network structure learning [7], where specific parts of the model are considered to be carried over between tasks.”
Transfer Learning across Networks for Collective Classification (2013, methodology): “[12] proposed a TAMAR algorithm to transfer relational knowledge with Markov Logic Networks (MLNs) across relational domains.”