Ask HN: What's the best paper you've read in 2020? • Hacker News Board

Re: Ask HN: What's the best paper you've read in 2020?

#41

Post by accraze » Tue, Dec 08, 2020, 8:31 PM UTC

Three papers stick out for me in the IML / participatory machine learning space this year:

1) Michael, C. J., Acklin, D., & Scheuerman, J. (2020). On interactive machine learning and the potential of cognitive feedback. ArXiv:2003.10365 [Cs]. http://arxiv.org/abs/2003.10365

2) Denton, E., Hanna, A., Amironesei, R., Smart, A., Nicole, H., & Scheuerman, M. K. (2020). Bringing the people back in: Contesting benchmark machine learning datasets. ArXiv:2007.07399 [Cs]. http://arxiv.org/abs/2007.07399

3) Jo, E. S., & Gebru, T. (2020). Lessons from archives: Strategies for collecting sociocultural data in machine learning. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 306–316. https://doi.org/10.1145/3351095.3372829

Also a great read related to IML tooling for audio recognition:

1) Ishibashi, T., Nakao, Y., & Sugano, Y. (2020). Investigating audio data visualization for interactive sound recognition. Proceedings of the 25th International Conference on Intelligent User Interfaces, 67–77. https://doi.org/10.1145/3377325.3377483

Re: Ask HN: What's the best paper you've read in 2020?

#42

Post by thanksforthe42 » Tue, Dec 08, 2020, 8:35 PM UTC

groceryheist wrote: post #21

Measuring the predictability of life outcomes with a scientific mass collaboration. http://www.pnas.org/lookup/doi/10.1073/pnas.1915006117 You might think that it's possible to use machine learning to predict whether people will be successful using established socio-demographic, psychological, and educational metrics. It turns out that it's very hard and simple regression models outperform the fanciest machine learni…

Luck/Fortune is so critical.

Genetics and net worth can be blown away by a good or bad group of friends. And unfortunately you start having friends before you are concious enough to realize the impact.

Re: Ask HN: What's the best paper you've read in 2020?

#43

Post by AlotOfReading » Tue, Dec 08, 2020, 8:35 PM UTC

One that came across my desk this year was the Archaic Ghost Introgression paper (https://advances.sciencemag.org/content/6/7/eaax5097), which established genetic contribution from an unknown archaic species in modern West African populations. It's notable not only because of the cool findings, but also because the paper is a culmination of a whole number of broader advances.

Re: Ask HN: What's the best paper you've read in 2020?

#44

Post by thanksforthe42 » Tue, Dec 08, 2020, 8:37 PM UTC

bawolff wrote: post #38

As a meta observation, its fascinating how few of these are computer related. Which is actually great because it gives me something to read on subjects im not familar with.

Abstraction has made Programming a hybrid of Tradition/Authority/Science/Art.

It's nearly impossible to have a scientific paper on anything with abstraction. At best you can create some "after the fact" optimizations using time studies and statistics.

Re: Ask HN: What's the best paper you've read in 2020?

#45

Post by monroewalker » Tue, Dec 08, 2020, 8:39 PM UTC

bra-ket wrote: post #14

Some CogSci & Neuro papers I found interesting in 2020: Constantinescu, Alexandra O., Jill X. O’Reilly, and Timothy EJ Behrens. "Organizing conceptual knowledge in humans with a gridlike code." Science 352.6292 (2016): 1464-1468. Kriegeskorte, Nikolaus, and Katherine R. Storrs. "Grid cells for conceptual spaces?." Neuron 92.2 (2016): 280-284. Klukas, Mirko, Marcus Lewis, and Ila Fiete. "Efficient and flexible represe…

Thanks for putting this list together! I took some cog sci courses in college and have been meaning to dive more into the research around it and these papers seem like a good place to start. I expect to run into lots of jargon and concepts I don't understand. Would it be possible for me to reach out to you for questions when I'm unable to make sense of the content after having researched the unknown concepts online?

Re: Ask HN: What's the best paper you've read in 2020?

#46

Post by cratermoon » Tue, Dec 08, 2020, 8:41 PM UTC

dalbasal wrote: post #24

thom wrote: post #22

Probably few people interested in the subject matter here, but as a piece of gentle snark I found this wonderful: https://www.researchgate.net/publication/342317256_A_systema...

Not really a football fan... care to explain?

Tactical Periodization is a training program credited for the success of at least one star. This paper says, in short, there are no scientific studies proving it works. We'd give it the benefit of the doubt and wait for proof, but it's been 20 years and still nothing.

Re: Ask HN: What's the best paper you've read in 2020?

#47

Post by bra-ket » Tue, Dec 08, 2020, 8:44 PM UTC

monroewalker wrote: post #45

bra-ket wrote: post #14

Some CogSci & Neuro papers I found interesting in 2020: Constantinescu, Alexandra O., Jill X. O’Reilly, and Timothy EJ Behrens. "Organizing conceptual knowledge in humans with a gridlike code." Science 352.6292 (2016): 1464-1468. Kriegeskorte, Nikolaus, and Katherine R. Storrs. "Grid cells for conceptual spaces?." Neuron 92.2 (2016): 280-284. Klukas, Mirko, Marcus Lewis, and Ila Fiete. "Efficient and flexible represe…

Thanks for putting this list together! I took some cog sci courses in college and have been meaning to dive more into the research around it and these papers seem like a good place to start. I expect to run into lots of jargon and concepts I don't understand. Would it be possible for me to reach out to you for questions when I'm unable to make sense of the content after having researched the unknown concepts online?

sure, my email is in my profile.

I'm not an expert though, just curious about "mind computations".

Re: Ask HN: What's the best paper you've read in 2020?

#48

Post by nhf » Tue, Dec 08, 2020, 8:47 PM UTC

groceryheist wrote: post #21

Measuring the predictability of life outcomes with a scientific mass collaboration. http://www.pnas.org/lookup/doi/10.1073/pnas.1915006117 You might think that it's possible to use machine learning to predict whether people will be successful using established socio-demographic, psychological, and educational metrics. It turns out that it's very hard and simple regression models outperform the fanciest machine learni…

> simple regression models outperform the fanciest machine learning ideas for this problem

This reminds me of a classic paper: "Improper linear models are those in which the weights of the predictor variables are obtained by some nonoptimal method; for example, they may be obtained on the basis of intuition, derived from simulating a clinical judge's predictions, or set to be equal. This article presents evidence that even such improper linear models are superior to clinical intuition when predicting a numerical criterion from numerical predictors."

Dawes, R. M. (1979). The robust beauty of improper linear models in decision making. American psychologist, 34(7), 571.

https://core.ac.uk/download/pdf/190386677.pdf

Re: Ask HN: What's the best paper you've read in 2020?

#49

Post by pasiaj » Tue, Dec 08, 2020, 8:49 PM UTC

abhgh wrote: post #19

screye wrote: post #12

The pair of these papers: (Don't read them in full.) 1.Attention is not explanation ( https://arxiv.org/abs/1902.10186 ) 2.Attention is not not Explanation ( https://arxiv.org/abs/1908.04626 ) Goes to show the complete lack of agreement between researchers in the explainability space. Most popular packages (allen NLP, google LIT, Captum) use saliency based methods (Integrated gradients) or Attention. The community ha…

I am following Tommi Jakkola in this space too. Also would recommended Ameet Talwalkar's group, esp the papers with Gregory Plumb like MAPLE [1]. [1] [PDF] https://papers.nips.cc/paper/2018/file/b495ce63ede0f4efc9eec...

Jaakkola – with two a's. Finnish names are weird.

Re: Ask HN: What's the best paper you've read in 2020?

#50

Post by Metacelsus » Tue, Dec 08, 2020, 8:54 PM UTC

ArtWomb wrote: post #3

Fresh today: Chromosome-scale, haplotype-resolved assembly of human genomes ;) https://www.nature.com/articles/s41587-020-0711-0

Yes, this is a big step forward! It's nice to not need to sequence genomes of both parents in order to resolve haplotypes.