Wenzhe Shi πŸ•πŸŽ (@trustswz) header
Wenzhe Shi πŸ•πŸŽ (@trustswz) profile picture

Leading AML at sharechat. Previously led recsys research team @twitter and CV research at Magic Pony (acquired by twitter). I train dogs and neural networks.

London, England
Joined November 2010
Photo by Wenzhe Shi πŸ•πŸŽ (@trustswz)Photo by Wenzhe Shi πŸ•πŸŽ (@trustswz)Photo by Wenzhe Shi πŸ•πŸŽ (@trustswz)Photo by Wenzhe Shi πŸ•πŸŽ (@trustswz)Photo by Wenzhe Shi πŸ•πŸŽ (@trustswz)Photo by Wenzhe Shi πŸ•πŸŽ (@trustswz)Photo by Wenzhe Shi πŸ•πŸŽ (@trustswz)Photo by Wenzhe Shi πŸ•πŸŽ (@trustswz)Photo by Wenzhe Shi πŸ•πŸŽ (@trustswz)
Wenzhe Shi πŸ•πŸŽ retweeted
We had a partial magic pony reunion tonight. Someone suggested starting another compression startup. Maybe call it mgc pny
8
2
129
Wenzhe Shi πŸ•πŸŽ retweeted
Speaking as someone who has worked on anti-spam against determined adversaries, I found this a nice, thoughtful thread on the reality of spam. Thank you @paraga.
Let’s talk about spam. And let’s do so with the benefit of data, facts, and context…
13
76
5
845
The right way of counting spam users out of mDAU is to sample and verify out of mDAU instead of out of followers of one or multiple account. And this is what @Twitter has been doing to the best of its abilities.
Let’s talk about spam. And let’s do so with the benefit of data, facts, and context…
1
1
28
More scientific than whatever people are doing without access to non public information out here and 1000 times better than πŸ’© on Twitter. 🀣
1
1
5
@jack can be the middle man and @fhuszar can head the data science team 🀩 Come on all, we can do this as a team.
1
1
Wenzhe Shi πŸ•πŸŽ retweeted
Postdoc on Probabilistic Machine Learning with @ZoubinGhahrama1 and me in Cambridge. If you know anyone interested, please encourage them (or yourself) to apply. jobs.cam.ac.uk/job/34849/
1
38
3
143
Only two photos I took in NYC 🀣
1
18
Wenzhe Shi πŸ•πŸŽ retweeted
The #ECIR2022 industry poster session is very popular! Check out the two nice posters from my colleagues @Twitter πŸ™‚ @jjh
1
5
28
Wenzhe Shi πŸ•πŸŽ retweeted
This month I joined @TwitterResearch to work on their search and recommendation. I'm very excited to work with some amazing RecSys practitioners and apply my research knowledge in an actual real-world setting!πŸ˜ƒ It's 20% part-time, mainly I'm still assist. prof. at Radboud Uni.
15
4
157
Wenzhe Shi πŸ•πŸŽ retweeted
Good news at the end of the week. We are pleased to announce the reproducibility track for #RecSys2022: recsys.acm.org/recsys22/call… Let me repeat that... here is the call for reproducibility papers for #RecSys2022!
8
2
24
We describe a method for maximising long term engagements by using model-based reinforcement learning. The policy is then used to make decisions about whether to send push notifications or not. More details are in the paper if you are interested. arxiv.org/abs/2202.08812
1
5
11
Wenzhe Shi πŸ•πŸŽ retweeted
βš οΈβ›ˆοΈ #StormEunice - be preparedβ›ˆοΈ ⚠️ With #Storm Eunice set to hit Surrey tomorrow, we are urging you to take extra care when out driving on the roads. β˜” Friday 0500 - 2100 Latest info πŸ‘‰ bit.ly/WxWarning Advice πŸ‘‰ bit.ly/3JDD97N Stay #WeatherAware⚠️
3
9
3
35
Wenzhe Shi πŸ•πŸŽ retweeted
Preliminary evidence suggests new Covid variant B.1.1.529 carries higher risk of reinfection than other variants, World Health Organization says bbc.in/30WLfap
327
1,004
407
2,096
Learning from Label Proportions: This line of research tries to learn from grouped training data where only aggregated group label is provided much like the recent change in Ads eco system. It also proofs that you can get good instance label prediction. arxiv.org/pdf/1402.5902.pdf
1
4
If you put it this way you see how ridiculous the labour shortage and #Brexit is. vm.tiktok.com/ZMR3mVNMT/
Checkout our team's recent paper where we took a deep dive into why multi-task learning models work well for post-click conversion prediction: arxiv.org/abs/2108.13475
1
7
Wenzhe Shi πŸ•πŸŽ retweeted
Photo from a Facebook friend. Starbucks at Shenzhen Airport in China.
51
335
169
1,872