When BERT Plays the Lottery, All Tickets Are Winning

EMNLP 2020  ·  Sai Prasanna, Anna Rogers, Anna Rumshisky ·

Large Transformer-based models were shown to be reducible to a smaller number of self-attention heads and layers. We consider this phenomenon from the perspective of the lottery ticket hypothesis, using both structured and magnitude pruning. For fine-tuned BERT, we show that (a) it is possible to find subnetworks achieving performance that is comparable with that of the full model, and (b) similarly-sized subnetworks sampled from the rest of the model perform worse. Strikingly, with structured pruning even the worst possible subnetworks remain highly trainable, indicating that most pre-trained BERT weights are potentially useful. We also study the "good" subnetworks to see if their success can be attributed to superior linguistic knowledge, but find them unstable, and not explained by meaningful self-attention patterns.

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract
No code implementations yet. Submit your code now

Tasks


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods