CS 8803 DMM: Data Management and Machine Learning
(Fall 2021)
Paper Review
For each research paper, the student must write a paper review, and submit the paper review in a given deadline on Canvas.
Submission Guideline
- Late submissions will not be accepted.
- Given unpredictable workloads students may have during the
semester, you are allowed to miss at most three reviews
during the semester.
Review Structure
Each review must contain the following information:
- Summary: (An overview of the main idea and contributions
in one paragraph)
- What is this paper about?
- What is the main contribution?
- Describe the main approach & results. Just facts, no
opinions yet.
- Summarize the insights resulting from the empirical study.
- Strength: (State at least three strengths of the paper)
- Is there a new theoretical insight? Or a significant
empirical advance?
- Did they solve a standing open problem? Or a good
formulation for a new problem? Or a faster/better solution
for an existing problem?
- Any good practical outcome (code, algorithm, etc)?
- Are the experiments well executed?
- Useful for the community in general?
- What is the paper’s potential impact on the field?
- Other types of strengths you may think of ...
- Opportunities for Improvements: (State at least three weaknesses or opportunities of the paper)
- What can be done better? Any missing baselines? Missing datasets? Any odd design choices in the algorithm not explained
well?
- Quality of writing?
- Is there sufficient novelty in what they propose? Minor variation of previous work?
- Why should anyone care? Is the problem interesting and
significant?
- What (directly or indirectly related) new ideas did this
paper give you?
- How can your own research benefit from the insights
provided in the paper?
Grading
Each review will be evaluated on a 100 points scale:
- 30 points for summary
- 30 points for strengths
- 30 points for weaknesses/opportunities
- Bonus: 10 points for quality of writing (free of grammar mistakes and typos)