Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Deep Neural Networks for YouTube Recommendations

research.google.com

Post reply on HN
Print view View original

21–30 of 102 posts

Re: Deep Neural Networks for YouTube Recommendations

#21

Post by AndrewKemendo »

Eliezer wrote: post #10

I noticed that YouTube's recommendations had suddenly gotten better! I wondered if they were using a new statistical approach, or had just started really optimizing at all because the old recommendations were extremely naive. I'm actually a little disappointed to find out that it might just be another deep learning thing. (Yes, it works, but I feel like you learn a little less about problem structure when what you re…

Throwing passive aggressive shade at what is current state of the art in machine learning is unwarranted.

Re: Deep Neural Networks for YouTube Recommendations

#22

Post by dsco »

One of the very best recommendation engines I've encountered is the "Discover Weekly" playlist from Spotify. It's helped me reconsider my relationship to music which I basically thought was dead since I had hit a rut on exploring new artists.

There's an interesting presentation of how it's created on SlideShare

http://www.slideshare.net/MrChrisJohnson/from-idea-to-execut...

Re: Deep Neural Networks for YouTube Recommendations

#23

Post by boulos »

pcovington wrote: post #17

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 general also welcome.

Perhaps I missed it, but there doesn't seem to be a comparison to the previous system. Is Hidden Layers "None" a good proxy?

Re: Deep Neural Networks for YouTube Recommendations

#24

Post by alphydan »

robinduckett wrote: post #18
Rotonde wrote: post #14

Earlier quoted context omitted.

That's curious, because in my opinion YouTube recommendations haven't been any good since 2009. Instead of getting interesting, strange and niche content, I'm bombarded with videos that have >100k views, feature clickbait titles and thumbnails and are generally incredibly low effort content. Methods that work better for a population as a whole might not work better for a large subset of that population, and might eve…

Maybe those are just the videos that you're statistically more likely to watch through to the end based on your viewing history...

Precisely. But that might be a local minimum. "Show him boobs and action trailers" is guaranteed to make him stay another 40min.

But perhaps there is a more risky strategy that takes longer to craft and actually delivers hours and hours of content to the user (but needs to fail longer before getting there).

Re: Deep Neural Networks for YouTube Recommendations

#25

Post by seanwilson »

dsco wrote: post #22

One of the very best recommendation engines I've encountered is the "Discover Weekly" playlist from Spotify. It's helped me reconsider my relationship to music which I basically thought was dead since I had hit a rut on exploring new artists. There's an interesting presentation of how it's created on SlideShare http://www.slideshare.net/MrChrisJohnson/from-idea-to-execut...

> One of the very best recommendation engines I've encountered is the "Discover Weekly" playlist from Spotify.

The addition of Discover Weekly really confused me. Shouldn't the features that create a radio station from an artist or a playlist fill this need already? Why is it only updated weekly? I haven't tried other services much but it feels like Spotify isn't doing as much as they can with recommendations.

Re: Deep Neural Networks for YouTube Recommendations

#26

Post by iverjo »

pcovington wrote: post #17

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 general also welcome.

Would love to see some more details on how you represent videos as feature vectors. Do you only use metadata provided by the uploaders (e.g. title and tags), or do you also analyze the raw video/audio somehow to augment the metadata?

Re: Deep Neural Networks for YouTube Recommendations

#27

Post by pcovington »

boulos wrote: post #23
pcovington wrote: post #17

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 general also welcome.

Perhaps I missed it, but there doesn't seem to be a comparison to the previous system. Is Hidden Layers "None" a good proxy?

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 found that recommendation systems are very difficult to evaluate offline.

Re: Deep Neural Networks for YouTube Recommendations

#28

Post by rainy-day »

I don't feel like anyone has gotten recommendations right, even though one seemingly obvious approach has not been tried by anyone: allow ratings of favorite works across all media: movies, tv shows, books, music, radio programs, youtube videos. Make a very easy, efficient UI to add ratings. This way you will avoid superficial matches: if I just watched an excellent steampunk cartoon, let's offer a zillion of throwaway crap steampunk. It's not the steampunk part that I liked, it's that it was amazingly done.

If I was a huge fan of books, movies, music, youtube picks of another user, it may be there is a deeper connection of the kind of quality we are both looking for, and so his or her recommendations would be highly relevant.

Re: Deep Neural Networks for YouTube Recommendations

#29

Post by pcovington »

iverjo wrote: post #26
pcovington wrote: post #17

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 general also welcome.

Would love to see some more details on how you represent videos as feature vectors. Do you only use metadata provided by the uploaders (e.g. title and tags), or do you also analyze the raw video/audio somehow to augment the metadata?

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 collaborative filtering approaches. When we inspect them, nearby vectors have a surprising amount of semantic similarity.

Features about the videos such as titles and tags, as well as features derived from audio and video, are introduced in the ranking phase.

Re: Deep Neural Networks for YouTube Recommendations

#30

Post by brokenmachine »

thomasahle wrote: post #13
Eliezer wrote: post #10

I noticed that YouTube's recommendations had suddenly gotten better! I wondered if they were using a new statistical approach, or had just started really optimizing at all because the old recommendations were extremely naive. I'm actually a little disappointed to find out that it might just be another deep learning thing. (Yes, it works, but I feel like you learn a little less about problem structure when what you re…

Mine seem like they have gotten a lot more click-baity. I wonder if that's an artifact of their optimization goal.

Probably some part of it is that there's more clickbait videos being created now, which is making them get more views.

It's a vicious clickbaity cycle.

Post reply on HN