Dissecting Lottery Ticket Transformers: Structural and Behavioral Study of Sparse Neural Machine Translation
Recent work on the lottery ticket hypothesis has produced highly sparse Transformers for NMT while maintaining BLEU. However, it is unclear how such pruning techniques affect a model's learned representations. By probing Transformers with more and more low-magnitude weights pruned away, we find that complex semantic information is first to be degraded. Analysis of internal activations reveals that higher layers diverge most over the course of pruning, gradually becoming less complex than their dense counterparts. Meanwhile, early layers of sparse models begin to perform more encoding. Attention mechanisms remain remarkably consistent as sparsity increases.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Data Level Lottery Ticket Hypothesis for Vision Transformers
The conventional lottery ticket hypothesis (LTH) claims that there exists a sparse subnetwork within a dense neural network and a proper random initialization method called the winning ticket, such that it can be trained…
Analogical SimilarityInformativenessPlaying the lottery with rewards and multiple languages: lottery tickets in RL and NLP
The lottery ticket hypothesis proposes that over-parameterization of deep neural networks (DNNs) aids training by increasing the probability of a "lucky" sub-network initialization being present rather than by helping th…
image-classificationImage ClassificationReinforcement LearningReinforcement Learning (RL)Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets
Why does a Transformer that has memorized its training set wait thousands of steps before it generalizes? Existing accounts locate this delay in norm minimization, feature emergence, or the late discovery of sparse subne…
Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
The lottery ticket hypothesis (LTH) has shown that dense models contain highly sparse subnetworks (i.e., winning tickets) that can be trained in isolation to match full accuracy. Despite many exciting efforts being made,…
Lottery Tickets can have Structural Sparsity
The lottery ticket hypothesis (LTH) has shown that dense models contain highly sparse subnetworks (i.e., $\textit{winning tickets}$) that can be trained in isolation to match full accuracy. Despite many exciting efforts …