activity
20182022
most citedSemantically-Conditioned Negative Samples for Efficient Contrastive Learning

4 citations · 8 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CL2022

Aligned Weight Regularizers for Pruning Pretrained Neural Networks

James O' Neill, Sourav Dutta, Haytham Assem

While various avenues of research have been explored for iterative pruning, little is known what effect pruning has on zero-shot test performance and its potential implications on…

cs.LG20213 cited

Deep Neural Compression Via Concurrent Pruning and Self-Distillation

James O' Neill, Sourav Dutta, Haytham Assem

Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strat…

cs.LG20214 cited

Semantically-Conditioned Negative Samples for Efficient Contrastive Learning

James O' Neill, Danushka Bollegala

Negative sampling is a limiting factor w.r.t. the generalization of metric-learned neural networks. We show that uniform negative sampling provides little information about the cla…

cs.CL20211 cited

-Neighbor Based Curriculum Sampling for Sequence Prediction

James O' Neill, Danushka Bollegala

Multi-step ahead prediction in language models is challenging due to the discrepancy between training and test time processes. At test time, a sequence predictor is required to mak…

cs.CL2018

Meta-Embedding as Auxiliary Task Regularization

James O' Neill, Danushka Bollegala

Word embeddings have been shown to benefit from ensambling several word embedding sources, often carried out using straightforward mathematical operations over the set of word vect…

stat.ML2018

Siamese Capsule Networks

James O' Neill

Capsule Networks have shown encouraging results on \textit{defacto} benchmark computer vision datasets such as MNIST, CIFAR and smallNORB. Although, they are yet to be tested on ta…