Graph machine learning researcher @Livermore_Lab. @UMich ‘20 PhD @WUSTL ‘15 AB/MS. Chess master and powerlifter.
Joined January 2016
- Tweets95
- Following118
- Followers185
- Likes749
Mark Heimann retweeted
2. We take a deep look into graph contrastive learning and find that data-centric properties known to be crucial to the success of visual CL can fail to hold for graph CL. Paper: arxiv.org/abs/2208.02810 @puja_computes @lastgoodcaesar @EkdeepL @danaikoutra
Mark Heimann retweeted
Our fourth tutorial is held by Mark Andrew Heimann, Junchen Jin and Danai Koutra (@danaikoutra). The tutorial is about
+++ Network Embedding for Role Discovery: Concepts, Tools, and Applications +++.
Link:
markheimann.github.io/tutori…
Mark Heimann retweeted
Thanks @tangjiliang for sharing this interesting and thought-provoking work. In light of these new findings, we revisit the problem of heterophily for GNNs and discuss the reasons behind the seemingly different takeaways from different works. Check it out:
jiongzhu.net/revisiting-hete…
GNNs are widely believed to work well due to the homophily assumption and recent works design new architectures to overcome such heterophily-related limitations. Is Homophily a Necessity for Graph Neural Networks? the answer is in our new preprint: arxiv.org/abs/2106.06134
Mark Heimann retweeted
Proud of my PhD students @lastgoodcaesar and Tara Safavi for receiving the Best Student Paper Award at IEEE ICDM'19 for our work on "Distribution of Node Embeddings as Multiresolution Features for Graphs"! #ICDM #datamining #GoBlue
web.eecs.umich.edu/~dkoutra/…
Mark Heimann retweeted
efficient structural embeddings for weighted and directed networks, with focus on email networks and professional role inference; and @cbelth talking about when it's worth embedding higher-order networks and when it's not useful to do so. #michiganAI #GoBlue #kdd2019 #gemslab
Mark Heimann retweeted
Lots of proud advisor moments at #kdd2019! @YujunYan4 presenting work on interpretable GCN with incoming PhD student @jiong971; Di Jin entertaining the crowd with his work on latent network summarization that bridges node embeddings and summaries; @lastgoodcaesar presenting /n
Mark Heimann retweeted
The streak of blowaway presentations by @michigan_AI researchers continues with Mark Heimann's "REGAL: Representation Learning-based Graph Alignment". Fun fact: Mark is a world renowned chess player, holding multiple national championships and titles.
Mark Heimann retweeted
Prof. Danai Koutra's GEMS lab introduced a new hash-based network alignment algorithm, 2x faster & 20-50% more effective than previous algorithms. A true new gem! More on it in a recently accepted PAKDD paper, jointly with Mark Heimann & collaborators. tinyurl.com/y958fug4
ALT Prof. Danai Koutra's GEMS lab
Mark Heimann retweeted
A tie tonight against @MiamiProChess clinches the second seed in the #prochess Atlantic Division. We've got another date with @stlarchbishops next Tuesday night in the first round of the 2018 @PROChessLeague playoffs! #nervesofsteel
Mark Heimann retweeted
FM Mark Heimann, just in with ANOTHER GM win, this time against Julio Becerra! Pittsburgh is up 7-6 in the middle of a very tight last round against Miami.
Mark Heimann retweeted
Pittsburgh is solid against a 3-grandmaster Miami lineup, finishing the first round, 2.5-1.5. Shoutout to Mark Heimann, who in his debut records a nice win against GM Yuniesky Quesada Perez!
