Deep transfer via second-order Markov logic

By Jesse Davis, Pedro M. Domingos. 2009

249 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

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

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

A Comprehensive Survey on Transfer Learning (2019, neutral): “Measurement Related Algorithms Maximum Mean Discrepancy [28] [29] [30] [31] [32]· · · Kullback-Leibler Divergence [33] [34] [35] [36] [37]· · · Jensen-Shannon Divergence [38] [39] [40] [41] [42]· · · Bregman Divergence [43] [44] [45] [46] [47]· · · Hilbert-Schmidt Independence Criterion [48] [29] [4”
Feature-based transfer learning with real-world applications (2010, background): “Recently, statistical relational learning techniques dominate this context [125, 52].”
Transfer Learning via Relational Type Matching (2015, methodology): “Other algorithms such as DTM [2] and TODTLER [3] use MLNs to create a second-order representation from the source that is then used to instantiate clauses in the target domain.”
Learning Categories From Few Examples With Multi Model Knowledge Transfer (2014, methodology): “A large variety of methods have been studied to integrate in different ways the source and target information: boosting approaches [18], [9], KNN [26], Markov logic [27], graphical models [28].”
TrGraph: Cross-Network Transfer Learning via Common Signature Subgraphs (2015, methodology): “In this work, we also adopt the idea of graph transfer but focus on non-streaming scenarios for cross-network node classification.”
TODTLER: Two-Order-Deep Transfer Learning (2015, methodology): “Our experiments compare the performance of TODTLER to DTM, which is the state-of-the-art transfer learning approach for relational domains (Davis and Domingos 2009).”
A Decade Survey of Transfer Learning (2010–2020) (2020, background): “(b) Markov Logic Network [80]–[82], the Markov Logic Network can be demonstrated by finding similar relationships from two different domains to construct a mapping from the source domain to the target domain.”
A Survey on Transfer Learning (2010, background): “Davis and Domingos [52] proposed an approach to transferring relational knowledge based on a form of second-order Markov logic.”
Transfer Learning for Activity Recognition: A Survey (2013, unknown): “See [17, 41, 42, 43] for examples of relational-knowledge transfer.”
Transfer across Completely Different Feature Spaces via Spectral Embedding (2013, background): “For example, [11] finds the commonality among different tasks, such as common words, to attack NLP tasks.”
Heterogeneous Transfer Learning for Image Clustering via the SocialWeb (2009, methodology): “For those data that are in different feature spaces where no translator is available, Davis and Domingos (2008) proposed a Markov-logic-based transfer learning al-gorithm, which is called deep transfer , for transferring knowledge between biological domains and Web domains.”