Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Criticsby David Boetius, Stefan LeueFirst submitted to…
HyperInterval: Hypernetwork approach to training weight interval regions in continual learningby Patryk Krukowski, Anna Bielawska,…
Fairness-Accuracy Trade-Offs: A Causal Perspectiveby Drago Plecko, Elias BareinboimFirst submitted to arxiv on: 24 May…
Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Makingby Drago Plecko,…
Leveraging Logical Rules in Knowledge Editing: A Cherry on the Topby Keyuan Cheng, Muhammad Asif…
Encoder Embedding for General Graph and Node Classificationby Cencheng ShenFirst submitted to arxiv on: 24…
Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functionsby Luca Arnaboldi, Yatin Dandi,…
FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scalerby Hongyi Peng,…
Unlearning during Learning: An Efficient Federated Machine Unlearning Methodby Hanlin Gu, Gongxi Zhu, Jie Zhang,…
Editable Concept Bottleneck Modelsby Lijie Hu, Chenyang Ren, Zhengyu Hu, Hongbin Lin, Cheng-Long Wang, Hui…