Deep Tree Transductions - A Short Survey

Bacciu, Davide; Bruno, A. C.

doi:10.1007/978-3-030-16841-4_25

Cited by 7 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We believe such criticisms should be positively embraced by the community to pursue the growth of the field. Some attempts to provide a set of standardized data and methods appear now under development 1 . In relation to this challenge, recent progresses have been facilitated by the growth and wide adoption by the community of modern software packages for the adaptive processing of graphs.…”

Section: Discussionmentioning

confidence: 99%

“…Another interesting application field leverages graph learning methods for Natural Language Processing (NLP) tasks, where the input is usually represented as a sequence of tokens. By means of dependency parsers, we can augment the input as a tree [1] or as a graph and learn a model that takes into account the syntactic [71] and semantic [70] relations between tokens in the text. An example is neural machine translation, which can be formulated as a graph-to-sequence problem [8] to consider syntactic dependencies in the source and target sentence.…”

Section: Natural Language Processingmentioning

confidence: 99%

See 1 more Smart Citation

A Gentle Introduction to Deep Learning for Graphs

Bacciu,

Errica,

Micheli

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

The adaptive processing of graph data is a long-standing research topic which has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is designed as a tutorial introduction to the field of deep learning for graphs. It favours a consistent and progressive introduction of the main concepts and architectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view to the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. It introduces the basic building blocks that can be combined to design novel and effective neural models for graphs.The methodological exposition is complemented by a discussion of interesting research challenges and applications in the field.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Natural Language Processingmentioning

confidence: 99%

A Gentle Introduction to Deep Learning for Graphs

Bacciu,

Errica,

Micheli

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Lately, attention is shifting towards the generative use of such learned distribution. For example, Deep Learning models have been used with success to generate parse trees [20,21], intermediate representations of reasoning tasks [22], and more broadly for general structure-to-structure transduction [23]. One domain where deep generative models for graphs are used extensively is Cheminformatics.…”

Section: Related Workmentioning

confidence: 99%

Edge-based sequential graph generation with recurrent neural networks

2020

Self Cite

View full text Add to dashboard Cite

Graph generation with MachineLearning is an open problem with applications in various research fields. In this work, we propose to cast the generative process of a graph into a sequential one, relying on a node ordering procedure. We use this sequential process to design a novel generative model composed of two recurrent neural networks that learn to predict the edges of graphs: the first network generates one endpoint of each edge, while the second network generates the other endpoint conditioned on the state of the first. We test our approach extensively on five different datasets, comparing with two well-known baselines coming from graph literature, and two recurrent approaches, one of which holds state of the art performances. Evaluation is conducted considering quantitative and qualitative characteristics of the generated samples. Results show that our approach is able to yield novel, and unique graphs originating from very different distributions, while retaining structural properties very similar to those in the training sample. Under the proposed evaluation framework, our approach is able to reach performances comparable to the current state of the art on the graph generation task.

show abstract

“…Both challenges have been tackled over the years by a variety of approaches ranging from early works on recursive neural networks [11], to their more recent deep learning style re-factoring [17] (see [2] for a recent survey), and including kernel-based approaches [1], [12], [16] and generative models [5], [6], [8]. In this work, we focus in particular on the latter models, which are referred to as Hidden Tree Markov Models (HTMM), being obtained as a generalisation of the Hidden Markov Model (HMM) to the tree domain.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Tensor Factorisation for Bottom-up Hidden Tree Markov Models

Castellana

Bacciu

2019

2019 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Bottom-Up Hidden Tree Markov Model is a highly expressive model for tree-structured data. Unfortunately, it cannot be used in practice due to the intractable size of its state-transition matrix. We propose a new approximation which lies on the Tucker factorisation of tensors. The probabilistic interpretation of such approximation allows us to define a new probabilistic model for tree-structured data. Hence, we define the new approximated model and we derive its learning algorithm. Then, we empirically assess the effective power of the new model evaluating it on two different tasks. In both cases, our model outperforms the other approximated model known in the literature.

show abstract

Deep Tree Transductions - A Short Survey

Cited by 7 publications

References 17 publications

A Gentle Introduction to Deep Learning for Graphs

A Gentle Introduction to Deep Learning for Graphs

Edge-based sequential graph generation with recurrent neural networks

Bayesian Tensor Factorisation for Bottom-up Hidden Tree Markov Models

Contact Info

Product

Resources

About