2 papers
cs.LG2026
Never Skip a Batch: Dense Learning of Temporal GNNs via Adaptive Pseudo-Supervision
Alexander Panyshev, Dmitry Vinichenko, Oleg Travkin +2
Temporal graph networks suffer from irregular supervision in realworld dynamic graphs, as most minibatches contain few labeled events. The lack of labels leads to high-variance gra…
cs.CL2026
ALIEN: Aligned Entropy Head for Improving Uncertainty Estimation of LLMs
Artem Zabolotnyi, Roman Makarov, Mile Mitrovic +4
Uncertainty estimation remains a key challenge when adapting pre-trained language models to downstream classification tasks, with overconfidence often observed for difficult inputs…