Hi! I’m Tara, a final-year PhD candidate at the University of Michigan working with Danai Koutra. My research focuses on machine learning over graphs + text and relational knowledge representation. I’m currently supported by an NSF Graduate Research Fellowship and a Google Women Techmakers scholarship.
In June 2022, I will join Microsoft Research Redmond as a research scientist.
Recent news
- February 2022: Had a wonderful time virtually visiting the Samsung AI Center Toronto and giving an invited talk on graph + text learning. Thank you for the invitation!
- October 2021: Giving an invited talk at the PKGs workshop at AKBC 2021. Thanks for the invite!
- September 2021: Two papers to appear at EMNLP 2021 on knowledge bases + language models (survey, negative commonsense)!
- August 2021: Happy to be joining Semantic Scholar at the Allen Institute for AI for a fall internship.
- May 2021: Excited to return to Microsoft Research for an internship.
- May 2021: Giving a keynote about personalized activity representations at the PHKG workshop, co-located with the Knowledge Graph Conference. Thank you to the organizers for the invitation!
- April 2021: Giving a talk about the CoDEx benchmark at the Connected Data London (CDL) 2021 meetup! Thanks to the organizers for the invitation.
Selected publications
Also see Google Scholar, my CV.
-
Relational World Knowledge Representation in Contextual Language Models: A Review
Tara Safavi, Danai Koutra
EMNLP 2021 [PDF] -
NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases
Tara Safavi, Jing Zhu, Danai Koutra
EMNLP 2021 [PDF] -
CoDEx: A Comprehensive Knowledge Graph Completion Benchmark
Tara Safavi, Danai Koutra
EMNLP 2020 [PDF] [GitHub] -
Evaluating the Calibration of Knowledge Graph Embeddings for Trustworthy Link Prediction
Tara Safavi, Danai Koutra, Edgar Meij
EMNLP 2020 [PDF] -
Toward Activity Discovery in the Personal Web
Tara Safavi, Adam Fourney, Robert Sim, Marcin Juraszek, Shane Williams, Ned Friend, Danai Koutra, Paul N. Bennett
WSDM 2020 [PDF] [blog post] -
Distribution of Node Embeddings as Multiresolution Features for Graphs
Mark Heimann, Tara Safavi, Danai Koutra
ICDM 2019 [PDF]
Best student paper award -
REGAL: Representation Learning-based Graph Alignment
Mark Heimann, Haoming Shen, Tara Safavi, Danai Koutra
CIKM 2018 [PDF]
Misc
- My advice on applying for the NSF GRFP (updated periodically)
- Books I enjoyed recently:
- The Remains of the Day by Kazuo Ishiguro - narrated by Nicholas Guy Smith
- Alexander Hamilton by Ron Chernow
- The Adventures of Huckleberry Finn by Mark Twain - narrated by Elijah Wood
- A Promised Land by Barack Obama - narrated by the author
- The Master and Margarita by Mikhail Bulgakov - narrated by Julian Rhind-Tutt
- Homegoing by Yaa Gyasi
- Circe by Madeline Miller
- The Orphan Master’s Son by Adam Johnson
- The Wind-up Bird Chronicle by Haruki Murakami
- War and Peace by Leo Tolstoy - Pevear and Volokhonsky English translation