Practice — Modern Recommender Architectures (6 questions)

A short-video app ranks 2,000 candidates per request. Product wants to optimize "satisfying watch time" and says: "just train on watch time, and also keep clicks and likes up". Logs show click and expected watch time are negatively correlated across candidates (about -0.4), likes are rare (about 3 percent of views) and "not interested" taps are rarer still (0.3 percent). An engineer proposes a shared-bottom network with five heads and a fusion formula V = p_{\text{click}} + 0.02\,E[\text{watch}] + 3\,p_{\text{like}} - 10\,p_{\text{dislike}}. A second engineer proposes MMoE "because it is state of the art".

1. Pick the heads and the label definition for each (what is a positive, what is the regression target). Why is raw watch time a poor target?
2. In the formula above, one candidate has p_{\text{click}} = 0.18, E[\text{watch}] = 60 s, p_{\text{like}} = 0.05 and p_{\text{dislike}} = 0.002; another has 0.30, 12 s, 0.02 and 0.001. Compute both values and say which term decides the ranking and why that is a scaling problem.
3. A sweep of the watch weight from 0.001 to 0.005 on a candidate set moved the mean click probability of the top-20 slate from 0.653 to 0.079. What does that imply for how you set and ship the weights?
4. When would you move from shared-bottom to MMoE or PLE? What do you measure to decide, and what does the lesson's toy experiment say about adopting it by default?
5. Name two ways to make the fusion robust to the different scales of the heads.

Your ranker must use each user's last 10,000 events (item, action, timestamp). Latency budget for the ranker is 40 ms for 1,000 candidates. One engineer wants a SASRec-style Transformer over all 10,000 events; another wants DIN-style target attention with an MLP scorer over all 10,000 events for each candidate; a third says "just average the embeddings". Embedding dimension is 64 and there are 500M users.

1. Estimate the multiply-accumulates per request for (a) dot-product target attention over 10,000 events for 1,000 candidates, (b) one full self-attention layer over the 10,000 events, and (c) a DIN-style MLP scorer of about 20,600 MAC per pair. Which of them fits a 40 ms budget on one accelerator slice, and what would you do about the rest?
2. Estimate the storage for the histories as IDs (8 bytes) and as fp16 vectors, for 500M users.
3. Explain a retrieve-then-attend design (SIM or ETA style) and give the new cost if 200 events are retrieved.
4. When would you choose a SASRec-style user encoder over target attention, and how does BERT4Rec differ at serving time?
5. List three training or evaluation pitfalls specific to sequence models.