Policies and Requirements
Method assignments: These assignments focus on the practical aspects of implementing, training, and evaluating machine learning algorithms with graphs. These assignments are to be completed individually and will be graded based on code correctness and quality of results determined by model performance on unseen test data. Method assignments are to be completed individually.
Final project: Students are expected to identify and formulate a machine learning problem with graph data, develop and evaluate algorithm(s) that tackle the problem (ideally using real-world datasets), and analyze the results for interesting insights; see the provided Latex templates for details. Students should submit a proposal and a final report. Proposals will shared for class discussion, and each student will present his/her proposal including 1-2 most relevant papers in the class. This will afford opportunity for me and your classmates to provide feedback. In addition, all projects will be presented during the last week of the class:
Extra credit: Students can earn extra credits by relevant contributions to the course. These include, but are not limited to, analysis and report of research talks (e.g. see CS colloquium), effective participation on Blackboard, code and dataset contributions, etc. If you are reporting a research talk, please email your report within two weeks of the talk. The report should provide a concise summary of the research problems addressed in the presentation and draw connections to materials discussed in class. Please use the same template as homework assignments to report research talks.
Lateness: Late submission for homework assignments is not allowed, i.e., late after due date/time: zero mark. However, late submission for method assignments or projects is allowed: late within three days: 30% of the full grade reduction; after that: zero mark.
Collaboration and the Facebook rule: Students are encouraged to work together, and to teach and help each other. However, cheating is a very serious offense and will be revealed and reported to the dean office with no exception. Please always follow UML's Code of Academic Integrity. The Facebook Rule (CREDIT: Min-Yen Kan): This rule says you are free to virtually meet with fellow students and discuss assignments with them. Writing on a virtual board or piece of paper is acceptable during the meeting; however, you may not take any written (electronic or otherwise) record away from the meeting. This applies when the assignment is supposed to be an individual effort. After the meeting, engage in a half hour of mind-numbing activity (like catching up with your friends and family's activities on Facebook), before starting to work on the assignment. This will assure that you are able to reconstruct what you learned from the meeting, by yourself, using your own brain. You must always report names of your collaborators on your assignments.
Religious observance: Students who observe a specific religious holiday that overlaps with any due dates of the course, please let us know by the end of the first week of classes. I accommodate students of all faiths on an individual basis, and there will be no due date or exam on religious holidays.
Anti-Harassment (Adapted from ACL Anti-Harassment policy): The open exchange of ideas, the freedom of thought and expression, and respectful scientific debate are central to the aims and goals of this course. Harassment and hostile behavior in any form (including but not limited to harassment based on race, gender, religion, age, appearance, national origin, ancestry, disability, sexual orientation, gender identity, etc.,) are unwelcome in this course.
|