The Quiet Semi-Supervised Revolution

One fascinating trend is that the landscape of semi-supervised learning may be changing to something that looks more like [the above graph]. And that would change everything. First, these curves match one’s mental model of what semi-supervised approaches should do: more data should always be better. The gap between semi-supervised and supervised should be strictly positive even for data regimes where supervised learning does well. And increasingly this is happening at no cost and remarkably little additional complexity. The ‘magic zone’ starts lower, and equally importantly, it isn’t bounded in high data regimes.

The post is actually quite short and frames recent research in semi-supervised learning quite effectively. There are links at the end if you want to dig in further.


Want to receive more content like this in your inbox?