7 citations · 8 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Accumulative SGD Influence Estimation for Data Attribution
Yunxiao Shi, Shuo Yang, Yixin Su +2
Modern data-centric AI needs precise per-sample influence. Standard SGD-IE approximates leave-one-out effects by summing per-epoch surrogates and ignores cross-epoch compounding, w…
cs.LG2024★ 7 cited
A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
Ziwen Zhao, Yixin Su, Yuhua Li +3
Graph self-supervised learning (SSL) is now a go-to method for pre-training graph foundation models (GFMs). There is a wide variety of knowledge patterns embedded in the graph data…