Legitimate ground-truth-free metrics for deep uncertainty classification scoringby Arthur Pignet, Chiara Regniez, John KleinFirst submitted…
Don’t Just Pay Attention, PLANT It: Transfer L2R Models to Fine-tune Attention in Extreme Multi-Label…
Guided Game Level Repair via Explainable AIby Mahsa Bazzaz, Seth CooperFirst submitted to arxiv on:…
Understanding Aggregations of Proper Learners in Multiclass Classificationby Julian Asilis, Mikael Møller Høgsgaard, Grigoris VelegkasFirst…
FT-PrivacyScore: Personalized Privacy Scoring Service for Machine Learning Participationby Yuechun Gu, Jiajie He, Keke ChenFirst…
Reweighting Local Mimina with Tilted SAMby Tian Li, Tianyi Zhou, Jeffrey A. BilmesFirst submitted to…
Calibrating Practical Privacy Risks for Differentially Private Machine Learningby Yuechun Gu, Keke ChenFirst submitted to…
Is Function Similarity Over-Engineered? Building a Benchmarkby Rebecca Saul, Chang Liu, Noah Fleischmann, Richard Zak,…
Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure…
Choice Between Partial Trajectories: Disentangling Goals from Beliefsby Henrik Marklund, Benjamin Van RoyFirst submitted to…