Publications & Talks

Pre-Prints

Björn Deiseroth, Patrick Schramowski, Hikaru Shindo, Devendra Singh Dhami and Kristian Kersting,  LogicRank: Logic Induced Reranking for Generative Text-to-Image Systems.

Zhongjie Yu, Devendra Singh Dhami, Kristian Kersting, Sum-Product-Attention Networks: Leveraging Self-Attention in Probabilistic Circuits.

Matej Zečević, Devendra Singh Dhami, Petar Veličković and Kristian Kersting, Relating Graph Neural Networks to Structural Causal Models.

Devendra Singh Dhami, Siwen Yan, Gautam Kunapuli, David Page and Sriraam Natarajan, Beyond Textual Data: Predicting Drug-Drug Interactions from Molecular Structure Images using Siamese Neural Networks.

Devendra Singh Dhami, Siwen Yan and Sriraam Natarajan, Bridging Graph Neural Networks and Statistical Relational Learning: Relational One-Class GCN.

Published

2024

Simon Kohaut, Benedict Flade, Devendra Singh Dhami, Julian Eggert  and Kristian Kersting, Towards Probabilistic Clearance, Explanation and Optimization. International Conference on Unmanned Aircraft Systems (ICUAS).

Jonas Seng, Matej Zečević, Devendra Singh Dhami, and Kristian Kersting, Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG. International Conference on Representation Learning (ICLR) 

Daniel Ochs, Karsten Wiertz, Sebastian Bußmann, Krsitian Kersting and Devendra Singh Dhami, Effective Risk Detection for Natural Gas Pipelines using Low Resolution Satellite Images. Remote Sensing Journal (Communication)

Matej Zecevic, Devendra Singh Dhami and Kristian Kersting, Structural Causal Models Reveal Confounder Bias in Linear Program Modelling. Machine Learning Journal (MLJ) [Asian Conference on Machine Learning (ACML) Journal Track]

Hikaru Shindo, Manuel Brack, Gopika Sudhakaran, Devendra Singh Dhami, Patrick Schramowski and Kristian Kersting, DeiSAM: Segment Anything with Deictic Prompting. AAAI Workshop on Neuro-Symbolic Learning and Reasoning in the Era of Large Language Models (NucLeaR)

2023

Matej Zečević, Devendra Singh Dhami and  Kristian Kersting, Not All Causal Inference is the Same. Transactions on Machine Learning Research (TMLR)

Quentin Delfosse, Hikaru Shindo, Devendra Singh Dhami and Kristian Kersting, Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction. Neural Information Processing Systems (NeurIPS)

 Moritz Willig, Matej Zečević, Devendra Singh Dhami and Kristian Kersting, Do Not Marginalize Mechanisms, Rather Consolidate! Neural Information Processing Systems (NeurIPS)

Gopika Sudhakaran, Devendra Singh Dhami, Kristian Kersting and Stefan Roth, Vision Relation Transformer for Unbiased Scene Graph Generation. International Conference on Computer Vision (ICCV)

Arseny Skryagin, Daniel Ochs,  Devendra Singh Dhami and Kristian Kersting, Scalable Neural-Probabilistic Answer Set Programming. Journal of Artificial Intelligence Research (JAIR)

Matej Zečević, Moritz Willig, Devendra Singh Dhami and Kristian Kersting, Causal Parrots: Large Language Models May Talk Causality But Are Not Causal. Transactions on Machine Learning Research (TMLR)

Binon Teji, Swarup Roy, Devendra Singh Dhami, Dinabandhu Bhandari and Pietro Hiram Guzzi,  Graph Embedding Techniques for Predicting Missing Links in Biological Networks: An Empirical Evaluation.  IEEE Transactions on Emerging Topics in Computing (TETC)

Simon Kohaut, Benedict Flade, Devendra Singh Dhami, Julian Eggert and Kristian Kersting, Mission Design for Unmanned Aerial Vehicles using Hybrid Probabilistic Logic Programs. IEEE International Conference on Intelligent Transportation Systems (ITSC)

2022

Hikaru Shindo, Viktor Pfanschilling, Devendra Singh Dhami and Kristian Kersting, alphaILP: Thinking Visual Scenes as Differentiable Logic Programs.  To appear in Machine Learning Journal (MLJ)

Zhongjie Yu, Fabrizio Ventola, Nils Thoma, Devendra Singh Dhami, Martin Mundt and Kristian Kersting, Predictive Whittle Networks for Time Series, Conference on Uncertainty in Artificial Intelligence (UAI) 

Viktor Pfanschilling, Hikaru Shindo, Devendra Singh Dhami and Kristian Kersting, Sum-Product Loop Programming: From Probabilistic Circuits to Loop Programming, International Conference on Principles of Knowledge Representation and Reasoning (KR)

Arseny Skryagin, Wolfgang Stammer, Daniel Ochs, Devendra Singh Dhami and Kristian Kersting, Neural-Probabilistic Answer Set Programming, International Conference on Principles of Knowledge Representation and Reasoning (KR)

Mei Ling Fang*, Devendra Singh Dhami* and Kristian Kersting, DP-CTGAN: Differentially Private Medical Data Generation using CTGANs, Artificial Intelligence in Medicine (AIME) (*=equal contribution)

Matej Zečević, Florian Peter Busch, Devendra Singh Dhami and Kristian Kersting, Finding Structure and Causality in Linear Programs, ICLR Workshop on the Elements of Reasoning: Objects, Structure and Causality (OSC)

2021

Matej Zečević, Devendra Singh Dhami, Athresh Karanam, Sriraam Natarajan, and Kristian Kersting, Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models, Neural Information Processing Systems (NeurIPS). Also presented at UAI workshop on Tractable Probabilistic Modeling (TPM) [poster] and Eastern European Machine Learning Summer School (EEML)  [Best Poster Award].

Devendra Singh Dhami, Siwen Yan and Sriraam Natarajan, A Statistical Relational Approach to Learning Distance-based GCNs, Tenth International Workshop on Statistical Relational AI (StarAI) [poster].

Devendra Singh Dhami, Siwen Yan, Gautam Kunapuli and Sriraam Natarajan, Non-Parametric Learning of Embeddings for Relational Data using Gaifman Locality Theorem, International Conference on Inductive Logic Programming (ILP)  [poster] [video].

Fabrizio Ventola*, Devendra Singh Dhami* and Kristian Kersting, Generative Clausal Networks: Relational Decision Trees as Probabilistic Circuits, International Conference on Inductive Logic Programming (ILP) (*=equal contribution)  [poster] [video].

Devendra Singh Dhami, Mayukh Das and Sriraam Natarajan, Beyond Simple Images: Human Knowledge-Guided GANs for Clinical Data Generation, International Conference on Principles of Knowledge Representation and Reasoning (KR) [poster] [video].

Devendra Singh Dhami*, Siwen Yan*, Gautam Kunapuli, David Page and Sriraam Natarajan, Predicting Drug-Drug Interactions from Heterogeneous Data: An Embedding Approach, Artificial Intelligence in Medicine (AIME) (*=equal contribution) [poster] [video].

Mayukh Das, Devendra Singh Dhami, Yang Yu, Gautam Kunapuli and Sriraam Natarajan, Human-Guided Learning of Column Networks: Knowledge Injection for Relational Deep Learning, ACM India Joint International Conference on Data Science & Management of Data (CODS-COMAD) [video].

2020

Siwen Yan, Devendra Singh Dhami and Sriraam Natarajan, The Curious Case of Stacking Boosted Relational Dependency Networks, Workshop on I Can't Believe It's Not Better (ICBINB), NeurIPS [poster][spotlight presentation].

Devendra Singh Dhami, Mayukh Das and Sriraam Natarajan, Knowledge Intensive Learning of Generative adversarial Networks, Workshop on Knowledge-infused Mining and Learning (KiML), KDD [video] [Best Paper Award].

Devendra Singh Dhami, Siwen Yan, Gautam Kunapuli and Sriraam Natarajan, Non-Parametric Learning of Gaifman Models, Ninth International Workshop on Statistical Relational AI (StarAI) , AAAI [poster].

2019

Devendra Singh Dhami, Gautam Kunapuli and Sriraam Natarajan, Efficient Learning of Relational Gaifman Models using Probabilistic Logic, Probabilistic Logic Programming (PLP) workshop, ICLP.

Devendra Singh Dhami, Gautam Kunapuli, David Page and Sriraam Natarajan, Predicting Drug-Drug Interactions from Molecular Structure Images, in AI for Social Good - AAAI Fall Symposium.

Mayukh Das, Devendra Singh Dhami, Yang Yu, Gautam Kunapuli and Sriraam Natarajan, Knowledge-augmented Column Networks: Guiding Deep Learning with Advice, ICML Workshop on Human in the Loop Learning (HILL).

Mayukh Das, Devendra Singh Dhami, Gautam Kunapuli, Kristian Kersting, and Sriraam Natarajan, Fast Relational Probabilistic Inference and Learning: Approximate Counting via Hypergraphs, The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI).

2018

Devendra Singh Dhami, Gautam Kunapuli, Mayukh Das, David Page and Sriraam Natarajan, Drug-Drug Interaction Discovery: Kernel Learning from Heterogeneous Similarities, IEEE/ACM Conference on Connected Health: Applications, Systems & Engineering Technologies (CHASE).

Mayukh Das, Devendra Singh Dhami, Gautam Kunapuli, Kristian Kersting, and Sriraam Natarajan, Approximate Counting for Fast Inference and Learning in Probabilistic Programming, The International Conference on Probabilistic Programming (PROBPROG). [2-page Abstract]

2017

Devendra Singh Dhami, Ameet Soni, David Page and Sriraam Natarajan. Identifying Parkinson's Patients : A Functional Gradient Boosting Approach , AI in Medicine (AIME) .

Devendra Singh Dhami, David Leake and Sriraam Natarajan. Knowledge-based Morphological Classification of Galaxies from Vision Features , KnowPros workshop AAAI.

John M Billings, Maxwell Eder, William C Flood, Devendra Singh Dhami, Sriraam Natarajan and Christopher T Whitlow. Machine Learning Applications to Resting-State Functional MR Imaging Analysis , Neuroimaging Clinics of North America, Volume 27, Issue 4. 

Talks

Machine Learning in Healthcare, University of Texas at Dallas Outreach Program, April 2018.

Human-Allied Artificial Intelligence, University of Texas at Dallas AI Conference, April 2019.

Machine Learning Beyond Prediction, Data Science Club,  September 2019.

Neural Networks Strike Back, Sir M. Visvesvaraya Institute of Technology, October 2020.

Distance based Graph Convolutional Networks, Cyberinfrastructure for Network Science Center @ Indiana University, June 2021.

Deep Learning on Graphs, 2nd International Research Workshop on Advances Deep Learning and Applications (WADLA), February 2022.

Hybrid AI: The Way Forward with Applications to Satellite Data}, Forum on Hybrid AI: State of the Art, GeoInformatics Conference,  July 2022.