Tree Edit Distance Learning via Adaptive Symbol Embeddings

Benjamin Paaßen, Claudio Gallicchio, Alessio Micheli, Barbara Hammer
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:3976-3985, 2018.

Abstract

Metric learning has the aim to improve classification accuracy by learning a distance measure which brings data points from the same class closer together and pushes data points from different classes further apart. Recent research has demonstrated that metric learning approaches can also be applied to trees, such as molecular structures, abstract syntax trees of computer programs, or syntax trees of natural language, by learning the cost function of an edit distance, i.e. the costs of replacing, deleting, or inserting nodes in a tree. However, learning such costs directly may yield an edit distance which violates metric axioms, is challenging to interpret, and may not generalize well. In this contribution, we propose a novel metric learning approach for trees which we call embedding edit distance learning (BEDL) and which learns an edit distance indirectly by embedding the tree nodes as vectors, such that the Euclidean distance between those vectors supports class discrimination. We learn such embeddings by reducing the distance to prototypical trees from the same class and increasing the distance to prototypical trees from different classes. In our experiments, we show that BEDL improves upon the state-of-the-art in metric learning for trees on six benchmark data sets, ranging from computer science over biomedical data to a natural-language processing data set containing over 300,000 nodes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v80-paassen18a, title = {Tree Edit Distance Learning via Adaptive Symbol Embeddings}, author = {Paa{\ss}en, Benjamin and Gallicchio, Claudio and Micheli, Alessio and Hammer, Barbara}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {3976--3985}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/paassen18a/paassen18a.pdf}, url = {https://proceedings.mlr.press/v80/paassen18a.html}, abstract = {Metric learning has the aim to improve classification accuracy by learning a distance measure which brings data points from the same class closer together and pushes data points from different classes further apart. Recent research has demonstrated that metric learning approaches can also be applied to trees, such as molecular structures, abstract syntax trees of computer programs, or syntax trees of natural language, by learning the cost function of an edit distance, i.e. the costs of replacing, deleting, or inserting nodes in a tree. However, learning such costs directly may yield an edit distance which violates metric axioms, is challenging to interpret, and may not generalize well. In this contribution, we propose a novel metric learning approach for trees which we call embedding edit distance learning (BEDL) and which learns an edit distance indirectly by embedding the tree nodes as vectors, such that the Euclidean distance between those vectors supports class discrimination. We learn such embeddings by reducing the distance to prototypical trees from the same class and increasing the distance to prototypical trees from different classes. In our experiments, we show that BEDL improves upon the state-of-the-art in metric learning for trees on six benchmark data sets, ranging from computer science over biomedical data to a natural-language processing data set containing over 300,000 nodes.} }
Endnote
%0 Conference Paper %T Tree Edit Distance Learning via Adaptive Symbol Embeddings %A Benjamin Paaßen %A Claudio Gallicchio %A Alessio Micheli %A Barbara Hammer %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-paassen18a %I PMLR %P 3976--3985 %U https://proceedings.mlr.press/v80/paassen18a.html %V 80 %X Metric learning has the aim to improve classification accuracy by learning a distance measure which brings data points from the same class closer together and pushes data points from different classes further apart. Recent research has demonstrated that metric learning approaches can also be applied to trees, such as molecular structures, abstract syntax trees of computer programs, or syntax trees of natural language, by learning the cost function of an edit distance, i.e. the costs of replacing, deleting, or inserting nodes in a tree. However, learning such costs directly may yield an edit distance which violates metric axioms, is challenging to interpret, and may not generalize well. In this contribution, we propose a novel metric learning approach for trees which we call embedding edit distance learning (BEDL) and which learns an edit distance indirectly by embedding the tree nodes as vectors, such that the Euclidean distance between those vectors supports class discrimination. We learn such embeddings by reducing the distance to prototypical trees from the same class and increasing the distance to prototypical trees from different classes. In our experiments, we show that BEDL improves upon the state-of-the-art in metric learning for trees on six benchmark data sets, ranging from computer science over biomedical data to a natural-language processing data set containing over 300,000 nodes.
APA
Paaßen, B., Gallicchio, C., Micheli, A. & Hammer, B.. (2018). Tree Edit Distance Learning via Adaptive Symbol Embeddings. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:3976-3985 Available from https://proceedings.mlr.press/v80/paassen18a.html.

Related Material