Beyond graph neural networks with lifted relational neural networks

Šourek, Gustav; Železný, Filip; Kuželka, Ondřej

doi:10.1007/s10994-021-06017-3

Cited by 12 publications

(6 citation statements)

References 69 publications

(66 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further related work has introduced, for example, neuro-symbolic approaches that generate textual output in the form of domain-specific languages [ 46 , 47 ] or logic programs [ 48 , 49 ], where the description of simple concepts detected in the input examples is the foremost goal [ 50 – 52 ]. Lifted Neural Networks [ 53 ] encode deep relational learning to provide insights into complex relations that go beyond the current GNN capabilities. Furthermore, there exist approaches to incorporate logic-based symbolic domain knowledge into GNNs, with the goal to improve their performance [ 42 ].…”

Section: Introductionmentioning

confidence: 99%

Generating Explanations for Conceptual Validation of Graph Neural Networks: An Investigation of Symbolic Predicates Learned on Relevance-Ranked Sub-Graphs

et al. 2022

View full text Add to dashboard Cite

Graph Neural Networks (GNN) show good performance in relational data classification. However, their contribution to concept learning and the validation of their output from an application domain’s and user’s perspective have not been thoroughly studied. We argue that combining symbolic learning methods, such as Inductive Logic Programming (ILP), with statistical machine learning methods, especially GNNs, is an essential forward-looking step to perform powerful and validatable relational concept learning. In this contribution, we introduce a benchmark for the conceptual validation of GNN classification outputs. It consists of the symbolic representations of symmetric and non-symmetric figures that are taken from a well-known Kandinsky Pattern data set. We further provide a novel validation framework that can be used to generate comprehensible explanations with ILP on top of the relevance output of GNN explainers and human-expected relevance for concepts learned by GNNs. Our experiments conducted on our benchmark data set demonstrate that it is possible to extract symbolic concepts from the most relevant explanations that are representative of what a GNN has learned. Our findings open up a variety of avenues for future research on validatable explanations for GNNs.

show abstract

Section: Introductionmentioning

confidence: 99%

Generating Explanations for Conceptual Validation of Graph Neural Networks: An Investigation of Symbolic Predicates Learned on Relevance-Ranked Sub-Graphs

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The proposed method itself also heavily relies on the completeness of the used theory, in this case being the functional and phenotypical annotations of the S.cerevisiae genome. Potential remedies, while still retaining some training efficiency, could be the use of computationally expensive feature selection techniques or even lifted methods such as LRNNs (Lifted Relational Neural Networks) ( Šourek et al 2021 ).…”

Section: Discussionmentioning

confidence: 99%

Interpreting protein abundance in Saccharomyces cerevisiae through relational learning

Brunnsåker,

Kronström,

Tiukova

et al. 2024

Bioinformatics

View full text Add to dashboard Cite

Motivation Proteomic profiles reflect the functional readout of the physiological state of an organism. An increased understanding of what controls and defines protein abundances is of high scientific interest. Saccharomyces cerevisiae is a well studied model organism, and there is a large amount of structured knowledge on yeast systems biology in databases such as the Saccharomyces Genome Database, and highly curated genome-scale metabolic models like Yeast8. These data-sets, the result of decades of experiments, are abundant in information, and adhere to semantically meaningful ontologies. Results By representing this knowledge in an expressive Datalog database we generated data descriptors using relational learning that, when combined with supervised machine learning, enables us to predict protein abundances in an explainable manner. We learnt predictive relationships between protein abundances, function and phenotype; such as α-amino acid accumulations and deviations in chronological lifespan. We further demonstrate the power of this methodology on the proteins His4 and Ilv2, connecting qualitative biological concepts to quantified abundances. Availability and implementation All data and processing scripts are available at the following Github repository: https://github.com/DanielBrunnsaker/ProtPredict

show abstract

“…The great algebraic variance of the t-norm theory has allowed identifying parameterized (i.e. weighted) classes of t-norms [100,89] that are very close to standard neural computation patterns (e.g. ReLU or sigmoidal layers).…”

Section: Nn(nn_burglary [B]) :-Burglary(b) Nn(nn_earthquake [E]mentioning

confidence: 99%

From Statistical Relational to Neural Symbolic Artificial Intelligence: a Survey

Marra¹,

Dumančić²,

Manhaeve³

et al. 2021

Preprint

View full text Add to dashboard Cite

Neural-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning. This survey identifies several parallels across seven different dimensions between these two fields. These cannot only be used to characterize and position neuralsymbolic artificial intelligence approaches but also to identify a number of directions for further research.

show abstract

Beyond graph neural networks with lifted relational neural networks

Cited by 12 publications

References 69 publications

Generating Explanations for Conceptual Validation of Graph Neural Networks: An Investigation of Symbolic Predicates Learned on Relevance-Ranked Sub-Graphs

Generating Explanations for Conceptual Validation of Graph Neural Networks: An Investigation of Symbolic Predicates Learned on Relevance-Ranked Sub-Graphs

Interpreting protein abundance in Saccharomyces cerevisiae through relational learning

From Statistical Relational to Neural Symbolic Artificial Intelligence: a Survey

Contact Info

Product

Resources

About