Publications (39)
Unifying Deep Predicate Invention with Pre-trained Foundation Models
Qianwei Wang, Bowen Li, Zhanpeng Luo +6
Long-horizon robotic tasks are hard due to continuous state-action spaces and sparse feedback. Symbolic world models help by decomposing tasks into discrete predicates that capture…
Evaluating Ensemble Methods for News Recommender Systems
Alexander Gray, Noorhan Abbas
News recommendation is crucial for facilitating individuals' access to articles, particularly amid the increasingly digital landscape of news consumption. Consequently, extensive r…
Human-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AI
Dakuo Wang, Justin D. Weisz, Michael Muller +6
The rapid advancement of artificial intelligence (AI) is changing our lives in many ways. One application domain is data science. New techniques in automating the creation of AI, k…
LOA: Logical Optimal Actions for Text-based Interaction Games
Daiki Kimura, Subhajit Chaudhury, Masaki Ono +6
We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural ne…
Stochastic ADMM for Nonsmooth Optimization
Hua Ouyang, Niao He, Alexander Gray
We present a stochastic setting for optimization problems with nonsmooth convex separable objective functions over linear equality constraints. To solve such problems, we propose a…
Logical Credal Networks
Haifeng Qian, Radu Marinescu, Alexander Gray +5
This paper introduces Logical Credal Networks, an expressive probabilistic logic that generalizes many prior models that combine logic and probability. Given imprecise information…
Data-Distributed Weighted Majority and Online Mirror Descent
Hua Ouyang, Alexander Gray
In this paper, we focus on the question of the extent to which online learning can benefit from distributed computing. We focus on the setting in which agents online-learn coop…
Reinforcement Learning with External Knowledge by using Logical Neural Networks
Daiki Kimura, Subhajit Chaudhury, Akifumi Wachi +4
Conventional deep reinforcement learning methods are sample-inefficient and usually require a large number of training trials before convergence. Since such methods operate on an u…
Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency
Maxwell Crouse, Ramon Astudillo, Tahira Naseem +4
We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-supervised method for training a neural semantic parser. Conceptually, LOCCO can be viewed as…
Leveraging Semantic Parsing for Relation Linking over Knowledge Bases
Nandana Mihindukulasooriya, Gaetano Rossiello, Pavan Kapanipathi +6
Knowledgebase question answering systems are heavily dependent on relation extraction and linking modules. However, the task of extracting and linking relations from text to knowle…
Stochastic Smoothing for Nonsmooth Minimizations: Accelerating SGD by Exploiting Structure
Hua Ouyang, Alexander Gray
In this work we consider the stochastic minimization of nonsmooth convex loss functions, a central problem in machine learning. We propose a novel algorithm called Accelerated Nons…
Breaking through the classical Shannon entropy limit: A new frontier through logical semantics
Luis A. Lastras, Barry M. Trager, Jonathan Lenchner +4
Information theory has provided foundations for the theories of several application areas critical for modern society, including communications, computer storage, and AI. A key asp…
Foundations of Reasoning with Uncertainty via Real-valued Logics
Ronald Fagin, Ryan Riegel, Alexander Gray
Real-valued logics underlie an increasing number of neuro-symbolic approaches, though typically their logical inference capabilities are characterized only qualitatively. We provid…
Bilevel Learning for Bilevel Planning
Bowen Li, Tom Silver, Sebastian Scherer +1
A robot that learns from demonstrations should not just imitate what it sees -- it should understand the high-level concepts that are being demonstrated and generalize them to new…
Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion
Prithviraj Sen, Breno W. S. R. Carvalho, Ibrahim Abdelaziz +4
Recent interest in Knowledge Base Completion (KBC) has led to a plethora of approaches based on reinforcement learning, inductive logic programming and graph embeddings. In particu…
Local Support Vector Machines:Formulation and Analysis
Ravi Ganti, Alexander Gray
We provide a formulation for Local Support Vector Machines (LSVMs) that generalizes previous formulations, and brings out the explicit connections to local polynomial learning used…
Few-shot Policy (de)composition in Conversational Question Answering
Kyle Erwin, Guy Axelrod, Maria Chang +8
The task of policy compliance detection (PCD) is to determine if a scenario is in compliance with respect to a set of written policies. In a conversational setting, the results of…
A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases
Sumit Neelam, Udit Sharma, Hima Karanam +22
Knowledge Base Question Answering (KBQA) tasks that involve complex reasoning are emerging as an important research direction. However, most existing KBQA datasets focus primarily…
Logic Embeddings for Complex Query Answering
Francois Luus, Prithviraj Sen, Pavan Kapanipathi +4
Answering logical queries over incomplete knowledge bases is challenging because: 1) it calls for implicit link prediction, and 2) brute force answering of existential first-order…
UPAL: Unbiased Pool Based Active Learning
Ravi Ganti, Alexander Gray
In this paper we address the problem of pool based active learning, and provide an algorithm, called UPAL, that works by minimizing the unbiased estimator of the risk of a hypothes…
AutoAIViz: Opening the Blackbox of Automated Artificial Intelligence with Conditional Parallel Coordinates
Daniel Karl I. Weidele, Justin D. Weisz, Eno Oduor +4
Artificial Intelligence (AI) can now automate the algorithm selection, feature engineering, and hyperparameter tuning steps in a machine learning workflow. Commonly known as AutoML…
Neural Reasoning Networks: Efficient Interpretable Neural Networks With Automatic Textual Explanations
Stephen Carrow, Kyle Harper Erwin, Olga Vilenskaia +5
Recent advances in machine learning have led to a surge in adoption of neural networks for various tasks, but lack of interpretability remains an issue for many others in which an…
How can AI Automate End-to-End Data Science?
Charu Aggarwal, Djallel Bouneffouf, Horst Samulowitz +9
Data science is labor-intensive and human experts are scarce but heavily involved in every aspect of it. This makes data science time consuming and restricted to experts with the r…
LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking
Hang Jiang, Sairam Gurajada, Qiuhao Lu +5
Entity linking (EL), the task of disambiguating mentions in text by linking them to entities in a knowledge graph, is crucial for text understanding, question answering or conversa…
Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks
Prithviraj Sen, Breno W. S. R. de Carvalho, Ryan Riegel +1
Recent work on neuro-symbolic inductive logic programming has led to promising approaches that can learn explanatory rules from noisy, real-world data. While some proposals approxi…
The Clustering of AGN in the Sloan Digital Sky Survey
David A. Wake, Christopher J. Miller, Tiziana Di Matteo +6
We present the two--point correlation function (2PCF) of narrow-line active galactic nuclei (AGN) selected within the First Data Release of the Sloan Digital Sky Survey. Using a sa…
A Neuro-Symbolic Approach to Multi-Agent RL for Interpretability and Probabilistic Decision Making
Chitra Subramanian, Miao Liu, Naweed Khan +5
Multi-agent reinforcement learning (MARL) is well-suited for runtime decision-making in optimizing the performance of systems where multiple agents coexist and compete for shared r…
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar +27
Knowledge base question answering (KBQA)is an important task in Natural Language Processing. Existing approaches face significant challenges including complex question understandin…
Statistical Computations with AstroGrid and the Grid
Robert C Nichol, Garry Smith, Christopher J Miller +6
We outline our first steps towards marrying two new and emerging technologies; the Virtual Observatory (e.g, AstroGrid) and the computational grid. We discuss the construction of V…
The Three-Point Correlation Function of Luminous Red Galaxies in the Sloan Digital Sky Survey
Gauri V. Kulkarni, Robert C. Nichol, Ravi K. Sheth +3
We present measurements of the redshift-space three-point correlation function of 50,967 Luminous Red Galaxies (LRGs) from Data Release 3 (DR3) of the Sloan Digital Sky Survey (SDS…
Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning
Subhajit Chaudhury, Sarathkrishna Swaminathan, Daiki Kimura +8
Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do n…
MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types
Keerthiram Murugesan, Sarathkrishna Swaminathan, Soham Dan +9
With the growing interest in large language models, the need for evaluating the quality of machine text compared to reference (typically human-generated) text has become focal atte…
An ADMM Based Framework for AutoML Pipeline Configuration
Sijia Liu, Parikshit Ram, Deepak Vijaykeerthy +6
We study the AutoML problem of automatically configuring machine learning pipelines by jointly selecting algorithms and their appropriate hyper-parameters for all steps in supervis…
Neuro-Symbolic Reinforcement Learning with First-Order Logic
Daiki Kimura, Masaki Ono, Subhajit Chaudhury +6
Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast conv…
SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases
Sumit Neelam, Udit Sharma, Hima Karanam +21
Knowledge Base Question Answering (KBQA) tasks that in-volve complex reasoning are emerging as an important re-search direction. However, most KBQA systems struggle withgeneralizab…
Compositional Program Generation for Few-Shot Systematic Generalization
Tim Klinger, Luke Liu, Soham Dan +3
Compositional generalization is a key ability of humans that enables us to learn new concepts from only a handful examples. Neural machine learning models, including the now ubiqui…
Characterizing the Nonequilibrium Response of FeRh Thin Films using Time-Domain Thermoreflectance (TDTR)
Renee M. Harton, Alejandro Ceballos, Vivek Unikandanunni +4
Time-Domain Thermoreflectance (TDTR) characterization of FeRh throughout its first-order antiferromagnetic (AF) to ferromagnetic (FM) transition shows that the transient reflectanc…
Logical Neural Networks
Ryan Riegel, Alexander Gray, Francois Luus +12
We propose a novel framework seamlessly providing key properties of both neural nets (learning) and symbolic logic (knowledge and reasoning). Every neuron has a meaning as a compon…
Massive Science with VO and Grids
Robert Nichol, Garry Smith, Christopher Miller +7
There is a growing need for massive computational resources for the analysis of new astronomical datasets. To tackle this problem, we present here our first steps towards marrying…