Transfer Learning via Relational Type Matching

Kumaraswamy, Raksha; Odom, Phillip; Kersting, Kristian; Leake, David; Natarajan, Sriraam

doi:10.1109/icdm.2015.138

Cited by 44 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also compare TreeBoostler with TODTLER (Van Haaren et al 2015), a transfer learning method that lifts a source structure to second-order logic. We do not compare against the state-of-the-art algorithm LTL (Kumaraswamy et al 2015) because the complete transfer and theory refinement system is not available.…”

Section: Methodsmentioning

confidence: 99%

“…It uses previous useful second-order patterns learned in the source domain to bias the learning process in the target domain towards models that also have these patterns. LTL (Kumaraswamy et al 2015) compares types between source and target predicates and performs a matching. After that, it builds the first-order logic clauses in the target domain by performing a type-based tree construction.…”

Section: Transfer Learningmentioning

confidence: 99%

“…Two of these algorithms (Davis and Domingos 2009;Van Haaren et al 2015) transfer relational knowledge by creating a second-order representation of formulas from learned MLN. Other three algorithms Mihalkova and Mooney 2009;Kumaraswamy et al 2015) find predicate mappings through searching methods to perform transference of clauses learned from MLNs by mapping their predicates.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Transfer learning by mapping and revising boosted relational dependency networks

2020

View full text Add to dashboard Cite

Statistical machine learning algorithms usually assume the availability of data of considerable size to train the models. However, they would fail in addressing domains where data is difficult or expensive to obtain. Transfer learning has emerged to address this problem of learning from scarce data by relying on a model learned in a source domain where data is easy to obtain to be a starting point for the target domain. On the other hand, real-world data contains objects and their relations, usually gathered from noisy environments. Finding patterns through such uncertain relational data has been the focus of the Statistical Relational Learning (SRL) area. Thus, to address domains with scarce, relational, and uncertain data, in this paper, we propose TreeBoostler, an algorithm that transfers the SRL state-of-the-art Boosted Relational Dependency Networks learned in a source domain to the target domain. TreeBoostler first finds a mapping between pairs of predicates to accommodate the additive trees into the target vocabulary. After, it employs two theory revision operators devised to handle incorrect relational regression trees aiming at improving the performance of the mapped trees. In the experiments presented in this paper, TreeBoostler has successfully transferred knowledge between several distinct domains. Moreover, it performs comparably or better than learning from scratch methods in terms of accuracy and outperforms a transfer learning approach in terms of accuracy and runtime.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Transfer Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Transfer learning by mapping and revising boosted relational dependency networks

2020

View full text Add to dashboard Cite

show abstract

“…One of the studies related to analogical reasoning using first-order predicate logic is transfer learning using a probabilistic logic model (PLM) [18][19]. Transfer learning using PLM aims to generate a learning model for a completely different domain using a model trained for one domain.…”

Section: Introductionmentioning

confidence: 99%

Analogical Reasoning With Deep Learning-Based Symbolic Processing

Honda¹,

Hagiwara

2021

IEEE Access

View full text Add to dashboard Cite

The authors propose analogical reasoning systems based on first-order predicate logic using deep learning. The proposed systems consist of a model combining recursive neural networks and Word2Vec. When unknown data is input in this trained model, similar outputs to those of the trained data are obtained. Previous studies on symbolic inference using deep learning have focused on deductive and inductive inferences, and they require rule templates that are manually created and provided to the models in advance. However, it is not enough to infer unknown rules from a large amount of data on the Internet. Analogical reasoning is a mode of inference that attempts to solve a new case based on similarity. Thus, it enables inference of rules that were challenging to comprehend in previous studies. As a result of the experiments, unknown rules can be efficiently inferred from known rules contained in the knowledge bases. Using the proposed systems, the authors can extract unknown rules from five of the eight datasets consisting of three types of knowledge bases described in Prolog. The proposed method is the first case of analogical reasoning based on the first-order predicate logic using deep learning. Furthermore, the models used in the proposed systems have shown high robustness when using Word2Vec. For this reason, it is suggested that the practical applications of the proposed systems enable efficient inferences from a large amount of data that include noisy data on the Internet.

show abstract

“…Two of these algorithms Domingos 2009, Van Haaren et al 2015] transfer relational knowledge by creating a second-order representation of formulas from learned Markov Logic Networks (MLN) [Richardson and Domingos 2006]. Other three algorithms [Mihalkova et al 2007, Mihalkova and Mooney 2009, Kumaraswamy et al 2015 find predicate mappings through search methods to perform transference of clauses learned from MLNs by mapping their predicates.…”

Section: Introductionmentioning

confidence: 99%

Transfer Learning by Mapping and Revising Boosted Relational Dependency Networks

Santos

Paes²,

Zaverucha

2020

Anais Do Concurso De Teses E Dissertações Da SBC (CTD-SBC 2020)

View full text Add to dashboard Cite

Statistical machine learning algorithms usually assume that there is considerably-size data to train the models. However, they would fail in addressing domains where data is difficult or expensive to obtain. Transfer learning has emerged to address this problem of learning from scarce data by relying on a model learned in a source domain where data is easy to obtain to be a starting point for the target domain. On the other hand, real-world data contains objects and their relations, usually gathered from noisy environment. Finding patterns through such uncertain relational data has been the focus of the Statistical Relational Learning (SRL) area. Thus, to address domains with scarce, relational, and uncertain data, in this paper, we propose TreeBoostler, an algorithm that transfers the SRL state-of-the-art Boosted Relational Dependency Networks learned in a source domain to the target domain. TreeBoostler first finds a mapping between pairs of predicates to accommodate the additive trees into the target vocabulary. After, it employs two theory revision operators devised to handle incorrect relational regression trees aiming at improving the performance of the mapped trees. In the experiments presented in this paper, TreeBoostler has successfully transferred knowledge among several distinct domains. Moreover, it performs comparably or better than learning from scratch methods in terms of accuracy and outperforms a transfer learning approach in terms of accuracy and runtime.

show abstract

Transfer Learning via Relational Type Matching

Cited by 44 publications

References 9 publications

Transfer learning by mapping and revising boosted relational dependency networks

Transfer learning by mapping and revising boosted relational dependency networks

Analogical Reasoning With Deep Learning-Based Symbolic Processing

Transfer Learning by Mapping and Revising Boosted Relational Dependency Networks

Contact Info

Product

Resources

About