Grading

This course will have a mix of lectures and presentation of research papers, and will require reading and critiquing research papers. The grade will be given based on class participation, presenting and leading discussions on a topic, a few assignments, and a semester-long class project in small groups.

There are not any exams. This also means that your grade will significantly depend on your participation and discussions in the class, along with your presentation, assignments, and the class project. We assume that you are taking this class because you are interested in this topic, and having experience in reading papers and doing research/project. You will also do a class presentation and the instructor will go give you feedback before the presentation to have an experience in presentation and leading a discussion in this class. This is a relatively small class and the instructor expects to know and frequently interact with each of you. If you think you might miss several lectures and others' presentations, this class might not be a good fit for you.

Grading criteria:

• Class participation (5%): This includes both attending lectures and frequent participation in classes including presentations led by other students. If you see you are missing more than 3 classes during the semester, let the instructor know the reason and discuss with her a plan.

• Assignments (20%): There will be a small number of (2-3) assignments during the semester, and depending on the assignments, we may have peer grading supervised by the instructor and the TA. The assignment may be individual or in groups. Discussions with acknowledgment are allowed.

• Paper review (15%): There will be on short paper reviews where you will critique the papers discussed in the student presentations and directions of future work on that topic, two excused. You can discuss with 1-2 other students acknowledging the names, but must write your own review.

• Presentation and leading discussion of a research topic (20%): We will post a list of potential research papers and topics. You can select a topic and 1-2 important papers on that topic to present and lead the discussion of in a class. It will be done in groups of 3 students by default (group sizes may vary a little depending on the number of students enrolled and their interests). Some topics may require > 1 presentations. Feel free to choose a topic related to your class project or a different one based on your interests. Students are expected to cover the basics before presenting the research paper -- e.g., if you choose the topic "explainability of GNN", you should first give an overview of GNN. Note that all students are expected to read the papers and participate in the discussions, not only the students who are presenting/leading the discussions.
  
  Presenters will send their slides to Sudeepa at least 3 days before the presentation, and will have a meeting with Sudeepa for feedback before the presentation at least 2 days before the presentation.  Consider this task as if you are delivering the lecture.  

• Class project (40%): There will be a semester-long class project on a topic of your interest and relevant to the class in small groups of 2-3 students. We will post some possible topics. It can be 

  1. an open-ended research project that can potentially be a paper (you are encouraged to do so, especially if you are a PhD student or an MS/undergraduate student considering doing a PhD later - your effort decides the grade not the end results, in past seminar-style courses, some students were able to publish research or demonstration papers in top conferences following up on their projects!), 

  2. implementation, analysis, and experimental study and comparisons of known algorithms on a topic (causal inference in a network, causal inference for time series data, etc..), these projects are also helpful to put on your CV as experience. Make sure that you maintain a well-documented git repository for these projects.

  3. building a tool with GUI for an application related to causal inference - often such tools can be submitted for publications under the "demonstration track" of top conferences,

  4. analyzing real and synthetic datasets for a problem, possibly in another application domain,

  5. something else.

Projects focusing on only reading papers/writing surveys are discouraged. There will be three checkpoints - an initial proposal,  midterm update, and final report. You are expected to meet the TA regularly and with the instructor every few weeks. There will be a short in-class presentation at the end. Project grades will take into account your efforts/ results, and quality of related work survey, presentation, and final report.

Standards of Conduct: 

Under the Duke Community Standard, you are expected to submit your own work in this course, including homeworks, projects, and paper reviews, as permitted by the course policy.

While discussions are encouraged for homeworks and paper reviews, all students who participated in the discussion should be named in the submission. Further, other's homeworks, paper reviews, etc. cannot be copied. 

LLMs: We are now in the era of LLMs. LLMs can be a lot of fun and very useful tool as well. You can use LLMs to learn material in this class and practice problems. But LLMs should not be used to solve homeworks or write paper reviews in this class. Any other use of LLM must be acknowledged clearly. As an example, see the guideline text below published by ACM for using generative AI for writing papers submitted to ACM conferences. You should follow this if you use LLMs in your project or review.

"Generative AI tools and technologies, such as ChatGPT, may not be listed as authors of an ACM published Work. The use of generative AI tools and technologies to create content is permitted but must be fully disclosed in the Work. For example, the authors could include the following statement in the Acknowledgements section of the Work: ChatGPT was utilized to generate sections of this Work, including text, tables, graphs, code, data, citations, etc.). If you are uncertain ­about the need to disclose the use of a particular tool, err on the side of caution, and include a disclosure in the acknowledgements section of the Work."