Reparameterizing Hybrid Markov Logic Networks to handle Covariate-Shift in Representations

Anup Shakya, Abisha Thapa Magar, Somdeb Sarkhel, Deepak Venugopal
Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, PMLR 286:3749-3765, 2025.

Abstract

We utilize Hybrid Markov Logic Networks (HMLNs) to combine embeddings learned from a Deep Neural Network (DNN) with symbolic relational knowledge. Since a DNN may not always learn optimal embeddings, we develop a mixture model to reduce variance in the HMLN parameterization. Further, we perform inference in our model that is robust to covariate shifts that may occur in the DNN embeddings by reparameterizing the HMLN. We evaluate our approach on Graph Neural Networks and show that our approach outperforms state-of-the-art methods that combine relational knowledge with DNN embeddings when we introduce covariate shifts in the embeddings. Further, we demonstrate the utility of our approach in inferring latent student knowledge in a cognitive model called Deep Knowledge Tracing.

Cite this Paper

BibTeX
@InProceedings{pmlr-v286-shakya25a, title = {Reparameterizing Hybrid Markov Logic Networks to handle Covariate-Shift in Representations}, author = {Shakya, Anup and Magar, Abisha Thapa and Sarkhel, Somdeb and Venugopal, Deepak}, booktitle = {Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence}, pages = {3749--3765}, year = {2025}, editor = {Chiappa, Silvia and Magliacane, Sara}, volume = {286}, series = {Proceedings of Machine Learning Research}, month = {21--25 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v286/main/assets/shakya25a/shakya25a.pdf}, url = {https://proceedings.mlr.press/v286/shakya25a.html}, abstract = {We utilize Hybrid Markov Logic Networks (HMLNs) to combine embeddings learned from a Deep Neural Network (DNN) with symbolic relational knowledge. Since a DNN may not always learn optimal embeddings, we develop a mixture model to reduce variance in the HMLN parameterization. Further, we perform inference in our model that is robust to covariate shifts that may occur in the DNN embeddings by reparameterizing the HMLN. We evaluate our approach on Graph Neural Networks and show that our approach outperforms state-of-the-art methods that combine relational knowledge with DNN embeddings when we introduce covariate shifts in the embeddings. Further, we demonstrate the utility of our approach in inferring latent student knowledge in a cognitive model called Deep Knowledge Tracing.} }
Endnote
%0 Conference Paper %T Reparameterizing Hybrid Markov Logic Networks to handle Covariate-Shift in Representations %A Anup Shakya %A Abisha Thapa Magar %A Somdeb Sarkhel %A Deepak Venugopal %B Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2025 %E Silvia Chiappa %E Sara Magliacane %F pmlr-v286-shakya25a %I PMLR %P 3749--3765 %U https://proceedings.mlr.press/v286/shakya25a.html %V 286 %X We utilize Hybrid Markov Logic Networks (HMLNs) to combine embeddings learned from a Deep Neural Network (DNN) with symbolic relational knowledge. Since a DNN may not always learn optimal embeddings, we develop a mixture model to reduce variance in the HMLN parameterization. Further, we perform inference in our model that is robust to covariate shifts that may occur in the DNN embeddings by reparameterizing the HMLN. We evaluate our approach on Graph Neural Networks and show that our approach outperforms state-of-the-art methods that combine relational knowledge with DNN embeddings when we introduce covariate shifts in the embeddings. Further, we demonstrate the utility of our approach in inferring latent student knowledge in a cognitive model called Deep Knowledge Tracing.
APA
Shakya, A., Magar, A.T., Sarkhel, S. & Venugopal, D.. (2025). Reparameterizing Hybrid Markov Logic Networks to handle Covariate-Shift in Representations. Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 286:3749-3765 Available from https://proceedings.mlr.press/v286/shakya25a.html.

Related Material