In-n-Out: Calibrating Graph Neural Networks for Link Prediction
원문 초록
Deep neural networks are notoriously miscalibrated, i.e., their outputs do not reflect the true probability of the event we aim to predict. While networks for tabular or image data are usually overconfident, recent works have shown that graph neural networks (GNNs) show the opposite behavior for node-level classification. But what happens when we are predicting links? We show that, in this case, GNNs often exhibit a mixed behavior. More specifically, they may be overconfident in negative predictions while being underconfident in positive ones. Based on this observation, we propose IN-N-OUT, the first-ever method to calibrate GNNs for link prediction. IN-N-OUT is based on two simple intuitions: i) attributing true/false labels to an edge while respecting a GNNs prediction should cause but small fluctuations in that edge's embedding; and, conversely, ii) if we label that same edge contradicting our GNN, embeddings should change more substantially. An extensive experimental campaign shows that IN-N-OUT significantly improves the calibration of GNNs in link prediction, consistently outperforming the baselines available -- which are not designed for this specific task.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Demystifying Distributed Training of Graph Neural Networks for Link Prediction
Learnable Spatial-Temporal Positional Encoding for Link Prediction
Future Link Prediction Without Memory or Aggregation
VitaGraph: Building a Knowledge Graph for Biologically Relevant Learning Tasks
MUST: Multi-Scale Structural-Temporal Link Prediction Model for UAV Ad Hoc Networks
Structural Alignment in Link Prediction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.