Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Toward Calibrated, Fair, and accurate Deepfake Detection
Ryan Brown, Chris Russell
Deepfake detectors show large performance gaps across demographic groups. Existing fairness approaches require demographic labels, retraining, or sacrifice accuracy. We introduce F…
cs.LG2024
DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation
Pengyun Wang, Yadi Cao, Chris Russell +5
Graph domain adaptation has recently enabled knowledge transfer across different graphs. However, without the semantic information on target graphs, the performance on target graph…