Hinge-Loss Markov Random Fields and Probabilistic Soft Logic

By Stephen H. Bach, Matthias Broecheler, Bert Huang, Lise Getoor. 2015

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Logic Tensor Networks for Semantic Image Interpretation (2017, methodology): “The area of Statistical Relational Learning (SRL), or Statistical Artiﬁcial Intelligence (StarAI), seeks to combine data-driven learning, in the presence of uncertainty, with symbolic knowledge [29, 2, 13, 7, 26, 23].”
HoloClean: Holistic Data Repairs with Probabilistic Inference (2017, neutral): “Recently, declarative probabilistic frameworks, such as Deep-Dive [37], Alchemy [1], and PSL [4] have been introduced to facilitate the construction of large scale factor graphs.”
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language (2019, methodology): “Our work is very related to the integration of Markov Logic Networks (Richardson and Domingos, 2006) and Probabilistic Soft Logic (Bach et al., 2017) with word embeddings, which was applied to Recognizing Textual Entailment (RTE) and Semantic Textual Similarity (STS) tasks (Garrette et al., 2011, 20”
Spatial Knowledge Distillation to Aid Visual Reasoning (2018, unknown): “In order to reason about the spatial relations among the objects in a scene and textual mentions of those objects in the question, we choose Probabilistic Soft Logic (PSL) [2] as our reasoning engine.”
Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning (2023, unknown): “…example, statistical relational learning (SRL) systems such as Markov logic networks (Richardson and Domingos, 2006) and probabilistic soft logic (Bach et al., 2017) have demonstrated great promise in reasoning under uncertainty and integration with our framework would enable even more adaptive…”
Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “For example, people tend to trust other people when they share trusted contacts (Trusts(A,B) ∧ Trusts(B,C)⇒ Trusts(A,C)) [58], or, on a scientific research platform, it can be observed that authors citing each other tend to work in the same field (Cite(x, y) ∧ hasFieldA(x)⇒ hasFieldA(y)) [20].”
Harnessing Deep Neural Networks with Logic Rules (2016, methodology): “We encode the FOL rules using soft logic (Bach et al., 2015) for ﬂexible encoding and stable optimization.”
Neurosymbolic AI: the 3rd wave (2020, unknown): “Section 6 contains more information about the neurosymbolic AI systems in each of the above categories as part of a note which seeks to clarify the terminology being used in AI, ML and DL.”
On a Convex Logic Fragment for Learning and Reasoning (2018, unknown): “With this restriction, the authors are able to get convex optimization [21] for the most probable explanation (MPE) task avoiding the general intractability of MLNs and they also provide different approaches to estimate the rule weights [22].”
Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference (2020, unknown): “Besides, globally inferring the relations at the document level would also be intractable for them due to the high complexity and low scalability (Bach et al. 2017).”