Tips on reading papers

Table of Contents

Note from Simon Peter's Data Center class.

Why is reading papers relevant to you?

  • understand the latest developments
  • learn how to write and present ideas.
  • start with other people's ideas to feel the processes
  • read critically (ask questions and challenge assumptions)
  • at some point you need to write your own papers.

Some model questions?

  • What is the research project this paper addresses?
  • What are the contributions/novel insights?
  • What do I learn when reading this?
  • How are the results substantiated? (proofs/experiments/…)
  • What are the conclusions and broader impact?

Read a paper at least three times

  • First pass: provides the general idea
    • 5-10mins
    • read abs/intro/conclusion/section headings.
    • briefly check which references you know
  • Second pass: understand the content
    • 1 hour
    • read full paper, ignore details (proofs etc.)
    • find key points, take notes, check figures carefully to understand them.
    • mark references for future reading.
  • Third pass: understand the depth
    • 4-5 hours
    • fully understand everything, attention to detail (read related work).
    • try to re-implement experiments, make up own examples, etc.
    • question everything!
    • generate ideas for your work.

Author: Zihao Ye

Email: git@localhost

Date:

Last modified: 2022-08-12 Fri 09:07

Licensed under CC BY-NC 4.0