Parallel Neurosymbolic Integration with Concordia
Not on the map. Why?
Abstract (arXiv)
Parallel neurosymbolic architectures have been applied effectively in NLP by distilling knowledge from a logic theory into a deep model.However, prior art faces several limitations including supporting restricted forms of logic theories and relying on the assumption of independence between the logic and the deep network. We present Concordia, a framework overcoming the limitations of prior art. Concordia is agnostic both to the deep network and the logic theory offering support for a wide range of probabilistic theories. Our framework can support supervised training of both components and unsupervised training of the neural component. Concordia has been successfully applied to tasks beyond NLP and data classification, improving the accuracy of state-of-the-art on collective activity detection, entity linking and recommendation tasks.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 54 references that are in the map. First posted on arXiv 1 Jun 2023.
Builds on
25 of 54 references.
References · 25
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2017Mask R-CNNcited by 7,277
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
- 2017Neural Collaborative Filteringcited by 1,111
- 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 394
- 2017Learning Explanatory Rules from Noisy Datacited by 211
- 2020Self-Distillation Amplifies Regularization in Hilbert Spacecited by 173
- 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
- 2017Cross-Sentence N-ary Relation Extraction with Graph LSTMscited by 101
- 2017Logic Tensor Networks for Semantic Image Interpretationcited by 92
- 2019Learning Actor Relation Graphs for Group Activity Recognitioncited by 83
- 2019Probabilistic Logic Neural Networks for Reasoningcited by 69
13 more
- 2015Hinge-Loss Markov Random Fields and Probabilistic Soft Logiccited by 63
- 2019Augmenting Neural Networks with First-order Logiccited by 51
- 2019Embedding Symbolic Knowledge into Deep Networkscited by 49
- 2020Neural-Symbolic Integration: A Compositional Perspectivecited by 45
- 2021Knowledge Distillation as Semiparametric Inferencecited by 29
- 2015Neural Network Matrix Factorizationcited by 26
- 2020Relational Neural Machinescited by 19
- 2020Analyzing Differentiable Fuzzy Implicationscited by 15
- 2019Integrating Knowledge and Reasoning in Image Understandingcited by 12
- 2018Towards Neural Theorem Proving at Scalecited by 11
- 2018Deep Probabilistic Logic: A Unifying Framework for Indirect Supervisioncited by 9
- 2023Principled and Efficient Motif Finding for Structure Learning of Lifted Graphical Modelscited by 4
- 2020Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networkscited by 3
Built on by
Citing papers per year: 2024: 2.
2 papers.