Neuro-Symbolic AI - Selected Publications


Arxiv Pre-prints

  • Ryan Riegel, Alexander Gray, Francois Luus, Naweed Khan, Ndivhuwo Makondo, Ismail Yunus Akhalwaya, Haifeng Qian, Ronald Fagin, Francisco Barahona, Udit Sharma, Shajith Ikbal, Hima Karanam, Sumit Neelam, Ankita Likhyani, Santosh Srivastava. Logical Neural Networks (Arxiv)
  • Ronald Fagin, Ryan Riegel, Alexander Gray. Foundations of Reasoning with Uncertainty via Real-valued Logics (Arxiv)
  • Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Li, Pavan Kapanipathi, Kartik Talamadupula. Reading Comprehension as Natural Language Inference: A Semantic Analysis (Arxiv)
  • Nandana Mihindukulasooriya, Gaetano Rossiello, Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Mo Yu, Alfio Gliozzo, Salim Roukos, Alexander Gray. Leveraging Semantic Parsing for Relation Linking over Knowledge Bases (Arxiv)
  • Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramon Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue, Dinesh Garg, Alfio Gliozzo, Sairam Gurajada, Hima Karanam, Naweed Khan, Dinesh Khandelwal, Young-Suk Lee, Yunyao Li, Francois Luus, Ndivhuwo Makondo, Nandana Mihindukulasooriya, Tahira Naseem, Sumit Neelam, Lucian Popa, Revanth Reddy, Ryan Riegel, Gaetano Rossiello, Udit Sharma, G P Shrivatsa Bhargav, Mo Yu. Question Answering over Knowledge Bases by Leveraging Semantic Parsing and Neuro-Symbolic Reasoning (Arxiv)

 

ACL 2021

  • Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Kartik Talamadupula, Mrinmaya Sachan and Murray Campbell. Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations
  • Tahira Naseem, Srinivas Ravishankar, Nandana Mihindukulasooriya, Ibrahim Abdelaziz, Young-Suk Lee, Pavan Kapanipathi, Salim Roukos, Alfio Gliozzo, Alexander Gray.  A Semantics-aware Transformer Model of Relation Linking for Knowledge Base Question Answering
  • Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramón Fernandez Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue, Dinesh Garg, Alfio Gliozzo, Sairam Gurajada, Hima Karanam, Naweed Khan, Dinesh Khandelwal, Young-Suk Lee, Yunyao Li, Francois Luus, Ndivhuwo Makondo, Nandana Mihindukulasooriya, Tahira Naseem, Sumit Neelam, Lucian Popa, Revanth Gangi Reddy, Ryan Riegel, Gaetano Rossiello, Udit Sharma, G P Shrivatsa Bhargav, Mo Yu.  Leveraging Abstract Meaning Representation for Knowledge Base Question Answering (findings)
  • Shourya Aggarwal, Divyanshu Mandowara, Vishwajeet Agrawal, Dinesh Khandelwal, Parag Singla, Dinesh Garg. Explanations for CommonSenseQA: New Dataset and Models (Full Paper, Main conference)
  • Hang Jiang, Sairam Gurajada, Qiuhao Lu, Sumit Neelam, Lucian Popa, Prithviraj Sen, Yunyao Li and Alexander Gray. LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking (Full Paper, main conference)

 

ICML 2021

  • Rui Chen, Sanjeeb Dash, Tian Gao. Integer Programming for Causal Structure Learning in the Presence of Latent Variables. Selected for long presentation
  • Yue Yu, Tian Gao, Naiyu Yin, Qiang Ji. DAGs with No Curl: Efficient DAG Structure Learning
  • Tyler Chen, Thomas Trogdon, Shashanka Ubaru. Analysis of stochastic Lanczos quadrature for spectrum approximation (Selected for long presentation)
  • Dong Ki Kim, Miao Liu, Matthew Riemer, Chuangchuang Sun, Marwa Abdulhai, Golnaz Habibi, Sebastian Lopez-Cot, Gerald Tesauro, Jonathan How. A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
  • Vasilis Kalantzis, Georger Kollias, Shashanka Ubaru, Athanasios Nikolakopoulos, Kenneth L. Clarkson, and Lior Horesh. Projection techniques to update the truncated SVD of evolving matrices with applications

 

IJCAI 2021

  • Cameron Allen, Michael Katz, Tim Klinger, George Konidaris, Matthew Riemer, Gerald Tesauro. Efficient Black-Box Planning Using Macro-Actions with Focused Effects  
  • Alex Tuisov, Michael Katz. The Fewer the Merrier: Pruning Preferred Operators with Novelty  
  • Daniel Fišer, Daniel Gnad, Michael Katz, Joerg Hoffmann. Custom-Design of FDR Encodings: The Case of Red-Black Planning  

 

AAAI 2021

  • [Blue sky ideas paper] Grady Booch, Francesco Fabiano, Kiran Kate, Nick Linck, Keerthiram Murugesan, Lior Horesh, Nick Mattei, Francesca Rossi, Biplav Srivastava. Thinking Fast and Slow in AI
  • [Demo track] Mariana Bernagozzi, Sheema Usmani, Biplav Srivastava, Francesca Rossi. VEGA: a Virtual Environment for Exploring Gender Bias vs. Accuracy Trade-offs in AI Translation Services
  • Wei Zhang, Murray Campbell, Yang Yu, Sadhana Kumaravel. Circles are like Ellipses, or Ellipses are like Circles? Measuring the Degree of Asymmetry of Static and Contextual Word Embeddings and the Implications to Representation Learning (Arxiv)
  • Xiao Qin, Nasrullah Sheikh, Berthold Reinwald, and Lingfei Wu. Relation-aware Graph Attention Model with Adaptive Self-adversarial Training
  • Songtao Lu, Kaiqing Zhang, Tianyi Chen, Tamer Basar, and Lior Horesh. Decentralized policy gradient descent ascent for safe multi-agent reinforcement learning
  • Zelin Zhao, Chuang Gan, Jiajun Wu, Xiaoxiao Guo,  Joshua B. Tenenbaum. Augmenting Policy Learning with Routines Discovered from a Single Demonstration
  • [Demo track] Ibrahim Abdelaziz, Srinivas Ravishankar, Pavan Kapanipathi, Salim Roukos, Alexander Gray.  A SemanticParsing and Reasoning-Based Approach to Knowledge Base Question Answering
  • Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Pushkar Shukla, Sadhana Kumaravel, Gerald Tesauro, Kartik Talamadupula, Mrinmaya Sachan, Murray Campbell.  Text-based RL Agents with Common-sense Knowledge: New Challenges, Environments and Baselines (Arxiv)
  • Zijun Cui, Pavan Kapanipathi, Kartik Talamadupula, Tian Gao, Qiang Ji.  Type-augmented Relation Prediction in Knowledge Graphs (Arxiv)
  • Maxwell Crouse, Ibrahim Abdelaziz, Bassem Makni, Spencer Whitehead, Cristina Cornelio, Pavan Kapanipathi, Kavitha Srinivas, Veronika Thost, Michael Witbrock, Achille Fokoue.  A Deep Reinforcement LearningApproach to First-Order Logic Theorem Proving (Arxiv)

 

NeurIPS 2020

  • Songtao Lu, Meisam Razaviyayn, Bo Yang, Kejun Huang, and Mingyi Hong. Finding second order stationary points efficiently in smooth nonconvex linearly constrained optimization problems (Spotlight) (Arxiv)
  • Gang Wang*, Songtao Lu*, Georgios B. Giannakis, Gerald Tesauro, Jian Sun.  Decentralized TD tracking with linear function approximation and its finite-time analysis (equal contribution)
  • Chia-Yu Chen, Jiamin Ni, Songtao Lu, Xiaodong Cui, Pin-Yu Chen, Xiao Sun, Naigang Wang, Swagath Venkataramani, Vijayalakshmi Srinivasan, Wei Zhang, and Kailash Gopalakrishnan. ScaleCom: Scalable sparsified gradient compression for communication-efficient distributed training
  • Santosh Shrivastava, Dinesh Khandelwal, Dhiraj Madan, Dinesh Garg, Hima Karanam, L Venkata Subramaniam. Inductive Quantum Embedding
  • S. Ubaru, S. Dash, O. Gunluk, and A. Mazumdar. Multilabel Classification by Hierarchical Partitioning and Data-dependent Grouping (Arxiv)
  • N. Si, J. Blanchet, S. Ghosh, M.S. Squillante.  Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality (Spotlight)
  • Dennis Wei, Tian Gao, Yue Yu. DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks (Spotlight)
  • Youssef Mroueh, and Mattia Rigotti. Unbalanced Sobolev Descent (Arxiv)
  • Yu Chen, Lingfei Wu** and Mohammed J Zaki (**Corresponding Author). Iterative Deep Graph Learning for Graph Neural Networks: Better and  Robust Node Embeddings (Arxiv)
  • Amir Abboud, Arturs Backurs, Karl Bringmann, Marvin Kunnemann. Impossibility Results for Grammar-Compressed Linear Algebra

 

EMNLP 2020

  • Xiaoxiao Guo, Mo Yu, Yupeng Gao, Chuang Gan, Murray Campbell and Shiyu Chang. Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning [Long Track] (Arxiv)
  • Subhajit Chaudhury, Daiki Kimura, Kartik Talamadupula, Michiaki Tatsubori, Asim Munawar and Ryuki Tachibana. Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games (Arxiv)
  • Ryosuke Kohita, Akifumi Wachi, Y. Zhao, and Ryuki Tachibana. Q-learning with Language Model for Edit-based Unsupervised Summarization
  • Lu Zhang, Mo Yu, Tian Gao, Yue Yu. MCMH: Muti-chain multi-hop rules for Knowledge Graph Reasoning [Findings Track] 

 

AAAI 2020

  • Pavan Kapanipathi, Veronika Thost, Siva Sankalp Patel, Spencer Whitehead, Ibrahim Abdelaziz, Avinash Balakrishnan, Maria Chang, Kshitij Fadnis, Chulaka Gunasekara, Bassem Makni, Nicholas Mattei, Kartik Talamadupula, Achille Fokoue. Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks (Arxiv)
  • Debarun Bhattacharjya, Karthikeyan Shanmugam, Tian Gao, Nicholas Mattei, Kush Varshney, Dharmashankar Subramanian. Event-Driven Continuous Time Bayesian Networks (PDF)
  • Tengfei Ma, Patrick Ferber, Siyu Huo, Jie Chen, Michael Katz. Online Planner Selection with Graph Neural Networks and Adaptive Scheduling (Arxiv)
  • Michael Katz, Shirin Sohrabi. Reshaping Diverse Planning (PDF)
  • Michael Katz, Shirin Sohrabi, Octavian Udrea. Top-Quality Planning: Finding Practically Useful Sets of Best Plans (PDF)
  • Tian Gao, Dharmashankar Subramanian, Karthikeyan Shanmugam, Debarun Bhattacharjya, Nicholas Mattei. A Multi-Channel Neural Graphical Event Model with Negative Evidence (Arxiv)
  • Mengyang Gu, Debarun Bhattacharjya, Dharmashankar Subramanian. GaSPing for Utility (PDF)
  • Matthew Riemer, Ignacio Cases, Clemens Rosenbaum, Miao Liu, and Gerald Tesauro. On the Role of Weight Sharing During Deep Option Learning (Arxiv)
  • Xiang Ni, Jing Li, Wang Zhou, Mo Yu, Kun-Lung Wu. Generalizable Resource Allocation in Stream Processing via Deep Reinforcement Learning (Arxiv)
  • Sijia Liu, Parikshit Ram, Deepak Vijaykeerthi, Djallel Bouneffouf, Gregory Bramble, Horst Samulowitz, Dakuo Wang, Andrew R. Conn, Alexander G. Gray. An ADMM Based Framework for AutoML Pipeline Configuration (Arxiv)
  • Radu Marinescu, Akihiro Kishimoto, Adi Botea, Rina Dechter, Alexander T. Ihler. Anytime Recursive Best-First Search for Bounding Marginal MAP
  • Takayuki Osogami and Rudy Raymond. Determinantal reinforcement learning
  • Avinash Balakrishnan, Djallel Bouneffouf, Nicholas Mattei, Francesca Rossi. Incorporating Behavioral Constraints in Online AI Systems
  • Francesca Rossi, Nicholas Mattei. Building Ethically Bounded AI (PDF)
  • G P Shrivatsa Bhargav, Michael R. Glass, Dinesh Garg, Shirish Shevade, Saswati Dana, Dinesh Khandelwal, L Venkata Subramaniam, Alfio Gliozzo. Translucent Answer Predictions in Multi-Hop Reading Comprehension (PDF)
  • Oktie Hassanzadeh, Debarun Bhattacharjya, Mark Feblowitz, Kavitha Srinivas, Michael Perrone, Shirin Sohrabi and Michael Katz, Causal Knowledge Extraction Through Large-Scale Text Mining (Demo Track) (PDF)

 

IJCAI 2020

  • Hanning Gao*, Lingfei Wu*, Po Hu, and Fangli Xu (*Equally Contributed). RDF-to-Text Generation with Graph-augmented Structural Neural Encoders
  • Kai Shen*, Lingfei Wu*, Fangli Xu, Siliang Tang, Jun Xiao, Yueting Zhuang (*Equally Contributed).  Hierarchical Attention Based Spatial-Temporal Graph-to-Sequence Learning for Grounded Video Description
  • Yu Chen, Lingfei Wu**, and Mohammed J Zaki (**Corresponding Author). GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
  • Haifeng Qian. Neural Belief Reasoner
  • Debarun Bhattacharjya, Tian Gao, Dharmashankar Subramanian. Order-Dependent Event Models for Agent Interactions
  • Debarun Bhattacharjya, Dharmashankar Subramanian, Tian Gao. State Variable Effects in Graphical Event Models
  • Debarun Bhattacharjya, Tian Gao, Nicholas Mattei, Dharmashankar Subramanian. Cause-Effect Association between Event Pairs in Event Datasets

 

ICML 2020

  • Shiyu Chang*, Yang Zhang*, Mo Yu*, Tommi Jaakkola. Invariant Rationalization. (Equal contribution)
  • Haoran Sun, Songtao Lu, Mingyi Hong. Improving the sample and communication complexity for decentralized non-convex optimization: Joint gradient estimation and tracking
  • Sijia Liu*, Songtao Lu*, Xiangyi Chen, Yao Feng, Kaidi Xu, Abdullah AI-Dujaili, Mingyi Hong, Una-May O'Reilly. Min-max Optimization without gradients: Convergence and applications to black-box evasion and poisoning attacks (equal contribution)
  • Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss. Enhancing Simple Models by Exploiting What They Already Know
  • Akifumi Wachi, Yanan Sui. Safe Reinforcement Learning in Constrained Markov Decision Processes
  • Giuseppe Vietri, Steven Wu, Mark Bun, Thomas Steinke, Grace Tian. New Oracle-Efficient Algorithms for Private Synthetic Data Release

 

KDD 2020

  • Xiaojie Guo, Liang Zhao, Zhao Qin, Lingfei Wu, Amarda Shehu and Yanfang Ye. Node-Edge Co-disentangled Representation Learning for Attributed Graph Generation

 

ACL 2020

  • Ying Lin, Heng Ji, Fei Huang and Lingfei Wu. A Joint End-to-End Neural Model for Information Extraction with Global Features
  • Rajarshi Haldar, Lingfei Wu, JinJun Xiong and Julia Hockenmaier. A Multi-Perspective Architecture for Semantic Code Search
  • Wenhao Yu, Lingfei Wu, Qingkai Zeng, Shu Tao, Yu Deng and Meng Jiang. Crossing Variational Autoencoders for Answer Retrieval
  • Luyang Huang, Lingfei Wu and Lu Wang. Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward
  • Vittorio Castelli, Rishav Chakravarti, Saswati Dana, Anthony Ferritto, Radu Florian, Martin Franz, Dinesh Garg, Dinesh Khandelwal, Scott McCarley, Michael McCawley, Cezar Pendus, Saurabh Pujar, Salim Roukos, Andrzej Sakrajda, Avi Sil, Rosario Uceda-Sosa, Todd Ward, and Rong Zhang. The TechQA Dataset (PDF)
  • Michael Glass, Alfio Gliozzo, Rishav Chakravarti, Anthony Ferritto, G P Shrivatsa Bhargav, Dinesh Garg, and Avi Sil. Span Selection Pre-training for Question Answering (PDF)

 

ICLR 2020

  • Yu Chen, Lingfei Wu, Mohammed J. Zaki. Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
  • Ze Ye, Kin Sum Liu, Tengfei Ma, Jie Gao, Chao Chen. Curvature Graph Network

 

CVPR 2020

  • Zhonghao Wang, Mo Yu, Yunchao Wei, Rogerior Feris, Jinjun Xiong, Wen-mei Hwu, Thomas S Huang, Honghui Shi. Differential treatment for stuff and things: A simple unsupervised domain adaptation method for semantic segmentation.

 

AISTATS 2020

  • Fredrik D. Johansson, Dennis Wei, Michael Oberst, Tian Gao, Gabriel Brat, David Sontag, and Kush R. Varshney. Characterization of Overlap in Observational Studies

 

Journals 2020

  • Traub, R.D., Hawkins, K., Adams, N.E., Hall, S., Simon, A., Whittington, M.A. Layer 4 pyramidal neuron dendritic bursting underlies a post-stimulus visual cortical alpha rhythm.  Comm. Biol, 2020 [LINK]
  • Tsung-Hui Change, Mingyi Hong, Hoi-To Wai, Xinwei Zhang, and Songtao Lu. Distributed learning in the non-convex world: from batch to streaming data, and beyond, IEEE Signal Processing Magazine
  • Meisam Razaviyayn, Tianjian Huang, Songtao Lu, Maher Nouiehed, Maziar Sanjabi, Mingyi Hong. Non-convex min-max optimization: applications, challenges, and recent theoretical advances, IEEE Signal Processing Magazine
  • Songtao Lu,  Ioannis Tsaknakis, Mingyi Hong and Yongxin Chen. Hybrid block successive approximation for one-sided non-convex min-max problems: algorithms and applications,  IEEE Transactions on Signal Processing
  • Shuai Ma, Ruixin Yang, Yang He, Songtao Lu, Fuhui Zhou, Naofal Al-Dhahir, and Shiyin Li. Achieving channel capacity of visible light communication, IEEE Systems Journal
  • Chun Du, Shuai Ma, Yang He, Songtao Lu, Hang Li, Han Zhang and Shiyin Li. Non-orthogonal multiple access  for visible light communication IoT networks, Wireless Communications and Mobile Computing
  • Myklebust, H.O.V., Eidsvik, J., Sperstad, I.B., Bhattacharjya, D. Value of information analysis for complex simulator models: Application to wind farm maintenance, Forthcoming in Decision Analysis
  • Mourad Baïou, Francisco Barahona. Network strength games: the core and the nucleolus, Math. Program. 180(1): 117-136
  • Kenneth L. Clarkson, Bernd Gaertner, Johannes Lengler, May Szedlak. Random Sampling with Removal. Journal of Discrete and Computational Geometry
  • Cao Xiao, Trong Nghia Hoang, Shenda Hong, Tengfei Ma, and Jimeng Sun. CHEER: Rich Model Helps Poor Model via Knowledge Infusion, Transactions on Knowledge and Data Engineering (TKDE)
  • Linfeng Song, Zhiguo Wang, Mo Yu, Yue Zhang, Radu Florian, Daniel Gildea. Evidence Integration for Multi-hop Reading Comprehension with Graph Neural Networks, Transactions on Knowledge and Data Engineering (TKDE)
  • Clément Canonne, Ilias Diakonikolas, Daniel Kane, and Aistair Stewart. Testing Bayesian NetworksIEEE Transactions on Information Theory, 66(5)
  • Tianxiang Gao, Songtao Lu, Jia Liu, and Chris Chu. Leveraging two reference functions in block Bregman proximal gradient descent for non-convex and non-Lipschitz problems, IEEE Transactions on Signal Processing. (Major Revision, April 2020)
  • Rui S. Shibasaki, Mourad Baiou, Francisco Barahona, Philippe Mahey, Mauricio C. de Souza. Lagrangian bounds for large‐scale multicommodity network design: a comparison between Volume and Bundle methods, International Transactions in Operations Research (LINK)
  • Bernardo A. Mello, Anderson B. Beserra, and Yuhai Tu. Sequential modification of bacterial chemoreceptors is key for achieving accurate adaptation and high gain simultaneously, Nature Communications
  • Okada, Y. Khan, S. Curran, A. Ahtam, B. Hämäläinen, M.S., Traub, R.D., and Pearl, P.L. Epileptic activity intrinsically generated in the human cerebellum, Ann. Neurol, doi: 10.1002/ana.25779.   Online ahead of print
  • Marcio Moreno, Vítor Lourenço, Sandro Fiorini, Polyana Costa, Rafael Brandão, Daniel Civitarese, Renato Cerqueira. Managing Machine Learning Workflow Components, International Journal of Semantic Computing
  • Traub, R.D., Moeller, F., Rosch, R., Baldeweg, T., Whittington, M.A., Hall, S.P. Seizure initiation in infantile spasms vs. focal seizures: proposed common cellular mechanisms, Rev. Neurosci. 31: 181-200
  • Traub, R.D., Whittington, M.A., Maier, N., Schmitz, D., Nagy, J.I. Could electrical coupling contribute to the formation of cell assemblies? Rev. Neurosci. 31: 121-141
  • Edith Elkind, Umberto Grandi, Francesca Rossi, and Arkadii Slinko. Cognitive Hierarchy and Voting Manipulation in k-Approval Voting, Mathematical Social Sciences