Semantic-based regularization for learning and inference

By Michelangelo Diligenti, Marco Gori, Claudio Saccà. 2017

192 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Computer Networks and Communications

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 Computational Theory and Mathematics

In Computer Networks and Communications

Citations in the corpus

Integrating Learning and Reasoning with Deep Logic Models (2019, methodology): “Unlike in Semantic-based Regularization [8] or Logic Tensor Networks [9], the sensorial and reasoning layers can be jointly trained, so that the high-level weights imposing the output structure are jointly learned together with the neural network weights, processing the low-level input.”
DeepProbLog: Neural Probabilistic Logic Programming (2018, methodology): “[33, 34, 35, 36, 37, 38] all center around including logical background knowledge as a regularizer during training.”
Logic Tensor Networks for Semantic Image Interpretation (2017, background): “The area of Statistical Relational Learning (SRL), or statistical AI (StarAI), seeks to combine learning from data with symbolic knowledge in the presence of uncertainty [Wang and Domingos, 2008; Bröcheler et al., 2012; Gutmann et al., 2010; Diligenti et al., 2015; Rocktaschel et al., 2015; Ravkic e”
A Semantic Loss Function for Deep Learning with Symbolic Knowledge (2017, background): “, 2017) or logical constraints (Rocktäschel et al., 2015; Hu et al., 2016; Demeester et al., 2016; Stewart & Ermon, 2017; Minervini et al., 2017; Diligenti et al., 2017; Donadello et al., 2017) on the output of a neural network.”
Neuro-Symbolic = Neural + Logical + Probabilistic (2019, methodology): “For instance, [Diligenti et al., 2017] and [Donadello et al., 2017] use first-order logic to specify constraints on the output of the neural network, while [Demeester et al., 2016] and [Minervini et al., 2017] use logical IF-THEN rules, derived from expert knowledge, to enforce the embeddings to be…”
Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “The integration of logic rules into the learning algorithm is often accomplished via additional, semantic loss terms [10], [11], [13], [21], [83], [84], [85].”
Exploring End-to-End Differentiable Natural Logic Modeling (2020, methodology): “One uses symbolic constraints as regularizers to equip neural models with the corresponding inductive bias (Demeester et al., 2016; Diligenti et al., 2017; Donadello et al., 2017; Xu et al., 2018; Li and Srikumar, 2019).”
A Primal Dual Formulation For Deep Learning With Constraints (2019, methodology): “We also compare our constrained learning against Diligenti et al. [2017a]’s approach of using soft constraints, where the violation penalty is multiplied with a constant λ and added to the original loss.”
On a Convex Logic Fragment for Learning and Reasoning (2018, background): “However, our approach is more in the spirit of [23] where semantic-based regularization (SBR), a unified framework for inference and learning that is centered around the notion of constraints and of parsimony principle, is presented.”