Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

Jia-Bin Huang

Aug 6, 2021 • 9 tweets • 3 min read • Read on X

How to come up with research ideas?

Excited about starting doing research but have no clue?🤷‍♂️🤷🏻‍♀️ Here are some simple methods that I found useful in identifying initial directions.

Check out the thread below 👇

*Find a different dimension*

Just learn a cool idea from others? Think about how you could extend it to another dimension.

Ex: Text / audio / image / video / graph

*Relax assumptions*

Identify the underlying assumptions of existing work and try relaxing them to make it work in more unconstrained settings.

*Make more assumptions*

Take a general approach and tailor it to your SPECIFIC problem. You can then leverage all the domain knowledge (i.e., make more assumptions) to improve the method.

*Combine two ideas/problems*

"To steal ideas from one person is plagiarism. To steal from many is research." - Wilson Mizner

*Grab a powerful hammer and find all the nails*

Pay attention to new emerging tools in the community. Apply and adapt them on your problem.

*Add an adjective*

Given an existing idea X, add an adjective to make it
- slow➡️ fast
- batch➡️online
- sensitive➡️robust
- centralized➡️distributed
- single-step➡️progressive
- single-level➡️hierarchical
- fixed➡️adaptive, sth-aware
- data-hungry➡️data-efficient
and so on

*Stress test the state-of-the-art*

Don't simply run on the fixed, boring benchmark datasets. Try it out on diverse, unconstrained examples and see how it fails. It's a great way to identify limitations of existing work. This is where your work can fill the gap.

That's all! I would love to hear about your approaches for coming up with new ideas.

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @jbhuang0604

Jia-Bin Huang

@jbhuang0604

Oct 26, 2023

How to get unstuck?

"It doesn't work." 🤷‍♀️🤷‍♂️

In most research projects, ~99% of the time your experiments DO NOT work. What should we do to get ourselves unstuck? 🤔

Sharing some tips I found useful. 🧵

*Help your mentors help you*

Tell them:
1⃣ WHY did you do the experiments?
2⃣ HOW did you do the experiments?
3⃣ WHAT did you see from the results?

Your mentors have more experience than you and are willing to help.

But you have to help them help you.

*Make your experiments easy to understand*

If you only verbally describe why/how/what you did, it's difficult for others to fully understand the process.

👉 Visualize your workflow
👉 Document the details

Your mentors are more likely to catch some issues here and there.

Read 11 tweets

Jia-Bin Huang

@jbhuang0604

Jun 5, 2023

How to draw an overview figure?

Creating a clear and informative overview figure is crucial for visualizing HOW your method works.

But how? 🤔 Let's deep dive with 🐢

*Choose the right level of abstraction*

Simplifying complex procedures helps improve clarity.

Ask yourself what the key message you want to convey. Don't overwhelm your readers with unnecessary details.

*Think in terms of computational graph*

Most methods process some INPUT with some COMPUTATION to produce some OUTPUT.

Visualize the flow with a "computational graph".

• Nodes: Computation
• Arrows: Dependency

Read 14 tweets

Jia-Bin Huang

@jbhuang0604

May 30, 2023

How to write a rebuttal for a conference?

Writing an effective rebuttal helps answer questions, address reviewers' concerns, clarify misunderstandings, and help the AC make an informed decision.

But it takes work to write a good one. 😟

Sharing some tips I found useful. 🧵

*Start positive*

Start with summarizing all the strengths noted by the reviewers and adding quotes to provide evidence.

Remind the reviewers and AC of
"Why should this paper be accepted?"

*Neutralize negative comments*

AC and other reviewers may only see all the NEGATIVE comments you responded to.

Neutralize them.

limited novelty 👉 technical novelty
insufficient experiments 👉 experimental validation
missing baseline 👉 baseline comparison

Read 9 tweets

Jia-Bin Huang

@jbhuang0604

May 3, 2023

How to meet with your advisors/mentors?

If you are a grad student, having effective regular meetings with advisors or mentors is absolutely crucial for your success!

Here are some tips on how to make the most of it! 🧵

*Present results*

❌ Collect and present the results you got in the last week? Terrible idea! 😱

Your advisor sees your results for the first time in the meeting? It means they don't have time to understand and think about them.

✅ Share and discuss results async FREQUENTLY.

*Make an agenda*

❌ Dive into technical details too quickly.

✅ Make an agenda. Manage the meeting to ensure you cover all the topics you want to discuss.

Read 8 tweets

Jia-Bin Huang

@jbhuang0604

Apr 15, 2023

How to do experiments?

Junior students often feel stressed before the weekly meeting with their advisors because their experiments do not go well. 😩😰😱

Some tips on why, what, and how to do experiments. 🧵

*Why? 🤔*

❌ Do an experiment to get improved performance.
✅ Do an experiment to test a hypothesis.

Many students trying to show improved results with experiments are missing the point.

Your goal of experiments should be to validate/test your research questions.

*What? 🤔*

What experiments should we do?

This involves three main steps:
1⃣ identify key research questions
2⃣break them down into baby steps
3⃣design experiments that best answer those questions

Read 11 tweets

Jia-Bin Huang

@jbhuang0604

Apr 5, 2023

How to multitask?

Feeling overwhelmed with multiple tasks on your to-do list? 😩

How do we effectively manage and juggle between tasks? 🤹 🤹‍♂️ 🤹‍♀️ Some tips below.👇

*Calm down*

Don't panic! With good prioritization and strategy, I am sure you will nail this!

*Prioritization*

Multitasking is just an illusion of rapid context switches.

To do well, identify each task's importance and urgency and develop a strategy.