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

61–70 of 102 posts

Re: Deep Neural Networks for YouTube Recommendations

#61

Post by pcovington »

recsysman wrote: post #51
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.

Great paper! How do you guys deal with new users and new items with little or zero historical data? Seems like the model wouldn't have good latent factors for them

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 difficult because of the fixed output vocabulary and batch training. In practice, this model is best suited for the head of the distribution and other specialized recommenders handle extremely fresh/low viewcount items. Feature engineering is key for new content during the ranking phase.

Re: Deep Neural Networks for YouTube Recommendations

#62

Post by joe_the_user »

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.

Hi,

I am very interest in this. Deep NN are quite an interesting subject and something I'm personally quite curious about.

I also use youtube recommendations quite a lot for some fairly specialize interests [which I'll keep unstated for now]. My current impression has been that the recommendation system has only gotten worse in the last ten years and is now nearly broken (I get recommendations from third party websites now).

As I recall things, Youtube removed most user recommendation controls 5-10 years ago and the guesses it makes still haven't made up for this loss.

But there are other things I find even harder to understand. I find that when I'm not logged in, after choosing 5-10 videos, youtube will start to recommend good stuff, indeed things that I'd like on my regular recommendation list but which I never do see there.

My impression of my regular recommendations is that serves nothing but crudes averages, videos that I just assume someone pays Google to recommend. ("Sports" "celebrity fails", etc).

Which brings me to shock that the cream of the cream of AI somehow deploys this to me. I get that Convnets have made quantum leaps in image recognition competitions. AlphaGo was a clear advance. But where is the progress here? If the recommendation engine is categorizing videos, either the categorizations don't correspond to my experiences or its using the categorizations incorrectly. Broadly, my impression is the algorithm is swayed by whether a video is broadly popular rather than whether its in a given category. And I work hard to prune every off-topic suggested video or suggested topic, yet I get what seems like poor to worthless quality recommendations.

Re: Deep Neural Networks for YouTube Recommendations

#63

Post by m0rphling »

so_serious wrote: post #60
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.

I look at the Recommended section daily, and I find it very disappointing for several reasons: - the recommendations are very often not interesting to me because + they cater to the lowest common denominator (you won't believe these 10 hilarious fails, PewDiePie picks his nose, etc.) + I have already watched the video + a video has been in the Recommended section for weeks and I haven't clicked on it. What makes you…

Despite the negative connotation, I wholeheartedly agree with this assessment. I usually ignore YT's Recommended videos for the same reasons you describe.

Re: Deep Neural Networks for YouTube Recommendations

#65

Post by mempko »

sevenless wrote: post #48
hacker42 wrote: post #37

Earlier quoted context omitted.

Do you study the phenomenon of information bubbles at Google? Let's say, a German user just happens to watch some right-wing populist video claiming that we need to stop Merkel's refugee politics. The next day the user might receive plenty of recommendations in their feed that confirm the message in the first video. They happen to stumble upon a video of some party convention by an uprising German populist party, and…

What about the reverse scenario, though? Should someone who watches videos about refugee suffering be given anti-refugee video recommendations, lest they be dragged into a 'left wing ideology'? I don't see how that would be acceptable. Would Holocaust documentaries be 'diversified' with Holocaust denial videos? 'Information bubbles' have existed as long as people have had a choice of newspapers to buy and TV channels…

While information bubbles have existed as long as people had a choice, at least with a newspaper or TV channel, you have to read and watch a little to understand whether it fits your liking. You have to put some effort in.

With recommendation engines, your bubble, without effort, ossifies.

Re: Deep Neural Networks for YouTube Recommendations

#66

Post by tnones »

cscurmudgeon wrote: post #54
sevenless wrote: post #48

Earlier quoted context omitted.

What about the reverse scenario, though? Should someone who watches videos about refugee suffering be given anti-refugee video recommendations, lest they be dragged into a 'left wing ideology'? I don't see how that would be acceptable. Would Holocaust documentaries be 'diversified' with Holocaust denial videos? 'Information bubbles' have existed as long as people have had a choice of newspapers to buy and TV channels…

Ah good old moral relativism.

As opposed to planting your flag in the ground that your camp is always right and the outgroup is evil?

Re: Deep Neural Networks for YouTube Recommendations

#67

Post by ycombinatorMan »

cscurmudgeon wrote: post #54
sevenless wrote: post #48

Earlier quoted context omitted.

What about the reverse scenario, though? Should someone who watches videos about refugee suffering be given anti-refugee video recommendations, lest they be dragged into a 'left wing ideology'? I don't see how that would be acceptable. Would Holocaust documentaries be 'diversified' with Holocaust denial videos? 'Information bubbles' have existed as long as people have had a choice of newspapers to buy and TV channels…

Ah good old moral relativism.

Ah good ole' sociopathy

Re: Deep Neural Networks for YouTube Recommendations

#68

Post by bearzoo »

pcovington wrote: post #59
boto3 wrote: post #57

Earlier quoted context omitted.

Could you elaborate on "we learn high dimensional embeddings for each video in a fixed vocabulary and feed these embeddings into a feedforward neural network." So, each video is mapped to fixed size vector of floats? A user's history is now a matrix of size [number of videos, embedding size]? What are the other parameters in this sentence "Importantly, the embeddings are learned jointly with all other model parameter…

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 information after averaging, you need lots of dimensions to spread out disparate items. This is of course not optimal, as the network should be able to learn how best to summarize the sequence. In the paper, however, we emphasize the importance…

Have you experimented with replacing the averaging operation on the vectors with a recurrent network such as an LSTM. This way you can not ignore the temporal nature of the feedback (I have had success improving metrics doing this on implicit streaming video feedback).

Re: Deep Neural Networks for YouTube Recommendations

#69

Post by pcovington »

andreyk wrote: post #31
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.

"To correct for this, we feed the age of the training example as a feature during training" Does this mean something different from feeding the age of the video, relative to when the training example was recorded? Feeding in the age of the video seems like a fairly obvious idea and like it should train the network to favor newer videos. If it actually means how long ago the training example was recorded that is rathe…

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 general technique for removing bias inherent to any machine learning system. Since examples always come from the past, you often have to be careful to prevent any system from being overly biased towards historical behavior. You don't need any additional metadata about items (what's the age of a search query?) and it's more resilient to predicting in regions the model has never seen because you fix serving to the very end of the training window.

I tend to think the focus on recent behavior is an artifact of underfitting. Research into richer temporal modeling is needed and recurrent networks seem promising.

We debated internally whether to use the "deep" moniker - Alexnet was 8 layers, so maybe the threshold is 8? The depth seems sort of irrelevant since stacking layers is trivial once the basic architecture is in place.

Re: Deep Neural Networks for YouTube Recommendations

#70

Post by catnaroek »

During the last few months, YouTube has consistently recommended me videos I wasn't interested in (to put it in polite terms), in spite of the fact by now Google knows enough about me to answer quite reliably what I'm likely to be interested in. The only explanation that I can find is that their need to show me specific videos (what do they call it nowadays? “sponsored content”?) prevails over other considerations.
Post reply on HN