Graph Unlearning with Efficient Partial Retraining
PulseAugur coverage of Graph Unlearning with Efficient Partial Retraining — every cluster mentioning Graph Unlearning with Efficient Partial Retraining across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New GraphToxin Attack Reconstructs Deleted Data from GNNs
Researchers have developed GraphToxin, a novel attack capable of reconstructing entire unlearned graphs from graph neural networks (GNNs). This method goes beyond previous membership inference attacks by not only recove…
-
New CUNO framework tackles catastrophic unlearning in graph models
Researchers have developed CUNO, a new framework for graph unlearning designed to mitigate catastrophic unlearning, a phenomenon where model utility sharply declines with large amounts of deleted data. CUNO addresses th…
-
New GDGU method enables efficient data deletion from AI models
Researchers have developed a new method called GDGU for graph unlearning, designed to efficiently remove specific data from trained models without full retraining. This technique is particularly useful for electric vehi…