5 citations · 8 across the 7 of their papers we have counts for
7 papers
A Mathematical Framework and a Suite of Learning Techniques for Neural-Symbolic Systems
Charles Dickens, Connor Pryor, Changyu Gao +5
The field of Neural-Symbolic (NeSy) systems is growing rapidly. Proposed approaches show great promise in achieving symbiotic unions of neural and symbolic methods. However, a unif…
Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learning
Charles Dickens, Changyu Gao, Connor Pryor +2
We leverage convex and bilevel optimization techniques to develop a general gradient-based parameter learning framework for neural-symbolic (NeSy) systems. We demonstrate our frame…
Simplifying Distributed Neural Network Training on Massive Graphs: Randomized Partitions Improve Model Aggregation
Jiong Zhu, Aishwarya Reganti, Edward Huang +4
Distributed training of GNNs enables learning on massive graphs (e.g., social and e-commerce networks) that exceed the storage and computational capacity of a single machine. To re…
Emotion Recognition in Conversation using Probabilistic Soft Logic
Eriq Augustine, Pegah Jandaghi, Alon Albalak +4
Creating agents that can both appropriately respond to conversations and understand complex human linguistic tendencies and social cues has been a long standing challenge in the NL…
NeuPSL: Neural Probabilistic Soft Logic
Connor Pryor, Charles Dickens, Eriq Augustine +3
In this paper, we introduce Neural Probabilistic Soft Logic (NeuPSL), a novel neuro-symbolic (NeSy) framework that unites state-of-the-art symbolic reasoning with the low-level per…
Order-Invariant Cardinality Estimators Are Differentially Private
Charlie Dickens, Justin Thaler, Daniel Ting
We consider privacy in the context of streaming algorithms for cardinality estimation. We show that a large class of algorithms all satisfy -differential privacy, so long as (a)…
HyperFair: A Soft Approach to Integrating Fairness Criteria
Charles Dickens, Rishika Singh, Lise Getoor
Recommender systems are being employed across an increasingly diverse set of domains that can potentially make a significant social and individual impact. For this reason, consider…