6 citations · 6 across the 3 of their papers we have counts for
3 papers
cs.CV2022
Implicit Feature Decoupling with Depthwise Quantization
Iordanis Fostiropoulos, Barry Boehm
Quantization has been applied to multiple domains in Deep Neural Networks (DNNs). We propose Depthwise Quantization (DQ) where is applied to a decomposed su…
cs.LG2021
Graph Conditioned Sparse-Attention for Improved Source Code Understanding
Junyan Cheng, Iordanis Fostiropoulos, Barry Boehm
Transformer architectures have been successfully used in learning source code representations. The fusion between a graph representation like Abstract Syntax Tree (AST) and a sourc…
cs.LG2021★ 6 cited
GN-Transformer: Fusing Sequence and Graph Representation for Improved Code Summarization
Junyan Cheng, Iordanis Fostiropoulos, Barry Boehm
As opposed to natural languages, source code understanding is influenced by grammatical relationships between tokens regardless of their identifier name. Graph representations of s…