For the last few weeks, I have seen many principal investigators (PIs) and professors announcing positions in the search for new graduate students. However, very few offer suggestions on what to include in the application, research proposal, or statement of purpose. In my Ph.D., not only did I get to work with different research teams, but I was also in charge of writing research proposals that ranged from fellowship applications to applications for industry and government grants. I would like to share a few tips and suggestions on how to improve your research proposal for those seeking to apply to graduate school, specifically those with machine learning backgrounds. The suggestions here can easily be adopted to improve proposals for fellowships, grad school, grants, scholarships, etc. I don’t claim that following my advice here will guarantee success. However, in my years of experience writing proposals and being a researcher, the following components really helped me prepare successful and strong research proposals.
Like with anything you are writing, that first paragraph of your research proposal or statement of purpose should be clear and concise. Focus on making it about what your experience is and what topics you are specifically interested to investigate. You should seek to answer what is your topic of interest? Why you are interested in this topic (motivations should be clear and straight to the point), and a brief explanation of how you are thinking about approaching a future problem. It’s important to keep the introduction short and concise and let it serve as a high-level overview of what you are about to discuss in the proposal. Each of the sections that follow provides some guidance on how to strengthen the proposal, including what to include and what to avoid. It’s not an example of how to write the proposal but a recipe for strengthening and improving it.
Before thinking about the main points you are going to include in your proposal, think about the scope. There are so many things you can write about but you only have 1 or 2 pages to really make a strong case for why you are a strong candidate for the lab you are applying to. As you write your proposal you should think about a theme and how to keep everything concise. Defining a scope early on helps to focus on the important details you want to include in your proposal. Prepare a checklist of the most important points that should use as a guide for writing a strong proposal.
Be very specific about the topics and problems you are interested in. For instance, just saying that you are interested in robust machine learning may not be specific enough. Maybe state that you are particularly interested in understanding the linguistic knowledge learned by BERT models (this is a very rough example). The more specific you are the better. It shows that you have experience and an ability to scope the research. Along with this, mention a few of the research questions you are thinking about for the work you plan to conduct. These could be very rough research questions but they help to give the reviewer an indication that you are already thinking ahead about the work you will be conducting. That can only be a good sign for the reviewer.
You could be interested or are working on multiple topics which is not rare in machine learning research. Your job is to write a proposal in a coherent way, making sure to focus on an overarching theme. When researchers work on many different topics it could give a sign that they are not focused enough as a researcher. It could also show a lack of experience as well. Seasoned researchers are really good at providing a reasonable scope for their research projects and that’s quickly visible in the proposal. The scope and theme help to keep the proposals tidy and coherent.
Background refers to your professional experience, the background of the work you have done, and the one you intend to work on. You must be able to share your research experience, current background, and the precise topics you are highly motivated to investigate. This is typically easy to write about and you should already be an expert on this by now. In fact, as you go through this guide, you will see that I already assume you have a rough draft prepared. The hardest part is to find a theme that connects with the reviewer. You should definitely try to conduct a bit more research about the labs you are applying to and try to find themes that make sense to include. In some cases, PIs are interested in expanding the scope of the research lab and that’s where your unique expertise may be useful. Really, you should try different ways to showcase your work ethic, research goals, and resiliency as a researcher. The following important questions may pop up as you prepare your background and discuss your experience:
How important is my publication record? I see this question a lot. You are worried about the amount of publication you have affecting your chances to get accepted into your dream research lab. In my opinion, if the PI you are applying to cares too much about the number of publications it’s probably not a good idea to join this lab in the first place. I think this is just a myth. The number of publications alone doesn’t really say much about the quality of the researcher that you are and can be. With that said, I believe the number of publications is not so important if you are able to convince the reviewer that you are a keen learner and can go deep into a topic, including sharing your experience on how you overcome challenges along the way. The amount of publications is not the only indicator that reviewers are looking at. If you have other types of experiences like industry or teaching experience make sure to include and highlight those as well. Research experience can be demonstrated in many different ways not only through a high number of publications. If you break down what research consists of you will see tasks like team management, project management, experimentation, visualization, data processing, writing, reviewing, etc. These are all important to make a research project successful. Keep that in mind as you prepare your proposal and highlight the tasks that you are good at. There is always an opportunity to grow in other areas, that is expected.
What if the work of the research lab is unrelated to what you are currently studying or the theme you are focusing on? It could be the case that you are applying to a research lab that is doing work you are interested to investigate but are currently not involved in. Like I said earlier, there is still hope. Talk about your experience as a researcher and make it clear how you will be able to contribute. You may not be familiar with how to apply model X for topic Y but perhaps you have a lot of experience working with similar data Z which the lab is working with. There is usually something you can use to connect with the work the lab is conducting.
I don’t have much to say about the topic of “theme” here. The reason I include it as a separate section is to remind you of how important it is to find a theme for your proposal. You may be tempted to write about all the little details of your experience with the idea to impress the reviewer of your experience. However, in this case, typically, more means less. Determining the scope, your focus, and the specific topics you are interested in working on are more important. Less is more, but ensure you have compacted all the important stuff into a strong overarching theme. As an example, in my case, I worked on many different applied machine learning research projects in the context of social computing. I always focused on affective computing as a theme when writing proposals. This is my expertise and I always felt more comfortable writing about it. That’s the point. You should feel comfortable about what you are writing, otherwise, it will easily show in your proposal and you don’t want that.
As researchers, we are always tempted to talk about “our” work as the work you have conducted in the different teams and projects you have collaborated on. There is nothing wrong with that. However, a research proposal is about what “you” have done specifically. Think about it. It’s really hard to convince others, through writing, about what exactly your expertise is. So try to focus on specific contributions you have made to the different research projects you have worked in. Write extensively about your contributions to the research projects not the contributions of others. We can’t all be good at everything. It’s important to focus on your strengths as a researcher and use that as a theme for the proposal. Remember, for this one time, it’s all about what you are capable of, not the team. It’s your time to shine.
Besides the background and the work you have done in the past, you are expected to provide more details about the topics you are interested to work on. This goes back to my earlier point about showcasing your experience. Seasoned researchers are typically good at writing about ideas and potential methodologies they plan to use. Talk briefly about the problem, the data collection strategies, the methods you propose, and the types of experiments you will be conducting. It needs not to be something definitive, it just must show rigor, readiness, and expertise. In fact, in most cases, topics evolve or change over time. It could just end up that you work on something completely different from what you proposed initially. Don’t worry about that for now. Just take the chance to emphasize your expertise and hands-on abilities.
Most people don’t talk about this in academia, perhaps because time is a very delicate topic. However, timing is everything. With so many deadlines, course work, and life itself, a graduate student must possess excellent project and time management skills. You should know exactly how much time a set of experiments might take and mention that in the proposal. Give rough estimates because at the end of the day things change as I mentioned earlier. Your ability to manage the project and timeline of it will make you stand out as a researcher. Timing is critical for both the student and the PI.
Besides time, you can also try to include the different components involving the work you are proposing to work on. You don’t have a lot of room to express this in a 2-pages proposal but you can do your best to provide rough estimates to give the reviewer the confidence that you are thinking ahead and are aware of all these important things. This shows maturity and experience.
If there is room, slightly mention what could cause delays or could potentially be a constraint for the project so that the PI knows what to expect and plan ahead. For instance, if your work might requires multiple GPUs to run experiments for two months then those details are very important to include in the proposal. Just keep it very short and don’t get into too many details. But this is a good chance to showcase your awareness and project management skills.
You don’t need a future work section in a research proposal but I always considered including extra bits of information about myself that helped strengthen my application. In the past, I realized that being a researcher requires not only hard work but the ability to connect with the team and keep everyone motivated and encouraged. One way I kept research teams motivated is by discussing with them their future goals and objectives. Keeping that at the center of the discussion always allowed us to reflect on the importance of what we were working on. Displaying this in a proposal is not mandatory but if you have space in your proposal express what you ideally would love to get out of the experience. Are you planning for a postdoc or an industrial career? Sharing these goals shows that you are ambitious and that you are determined to succeed in the work you will conduct. Again, it’s all about showcasing the desire to grow.
Although the tools you will use don’t really matter that much at this point, it’s important to realize that besides your own work, you will be working in research teams in a lot of cases. Conduct a quick search on the projects published by the lab you are interested to join and make sure you are familiar or aware of the tools used by those researchers you might be working with. If you are not familiar with the tools, it shouldn’t matter that much but you should try to express in the proposal that you are willing to learn those frameworks and that you can do so easily given some timeframe. It’s all about making the reviewer feel confident about your expertise and ability to adapt. From what I have seen, integrity, maturity, and eagerness to learn are undoubtedly the best qualities of a seasoned researcher.
That’s all I have for you today. I believe that if you pay close attention to the points I discussed in this guide and apply them to your proposal it could give you an edge and an opportunity to join that dream research lab. I am sure that I didn’t cover a lot of other topics and questions that you may have. If that is the case, open an issue, and I will address them and continue refining the guide.
If you wish to hear more about my advice and tips, including different ML-related guides and topics, connect with me on Twitter or follow my blog.
- The guide is basically in draft mode. If you have feedback or grammar corrections please let me know by opening an issue.
- Add more components that in your experience helped research proposals stand out
- It will be great to add more examples to each section