Viewing profile — pcovington

Your intuition is correct - there are other ways to capture the non-stationary nature of this particular problem. We thought that the example age approach is neat because it is a g…

Thanks! This model handles new users gracefully because it can fallback to demographic/geographic priors and gradually specialize as the user watches videos. New items are difficul…

Figure 3 illustrates that the variable sized watch history is combined with an average operation. This is partially why the embeddings need to be so large - in order to retain info…

This is a very natural avenue and an active area of research at Google/Deep Mind. Stay tuned...

word2vec did inspire earlier iterations of the model, but the key insight is that embeddings are learned jointly with all other model parameters. There is no separate source of emb…

There are many close collaborations between product and research, as well as direct exchanges between different product areas. Close collaboration is key because those working dire…

YouTube has used machine learning in recommendations for many years. We have struggled with interpretability, both while debugging mistakes made by the system and exposing plausibl…

The video embeddings in the paper are learned purely based on observing what users co-watch in sessions. In this sense, they can be thought of as latent factors in more traditional…

Yes, it's a reasonable proxy. It was challenging to set up similar experiments with the old system because it was trained to approximate a different "surrogate" problem. We've also…

Author here - happy to answer questions about the techniques in the paper. We're super excited to finally share this work externally. Feedback about YouTube recommendations in gene…