no code implementations • 19 Feb 2024 • Yanbang Wang, Hejie Cui, Jon Kleinberg
Moreover, we find that more advanced LLMs have a striking dependence on the domain that a real-world graph comes from -- by yielding the best recall accuracy when the graph is narrated in a language style consistent with its original domain.
no code implementations • 16 Jan 2024 • Yanbang Wang, Jon Kleinberg
Such a modeling choice typically involves an underlying projection process that maps the original hypergraph onto a graph, and is common in graph-based analysis.
no code implementations • 23 Nov 2022 • Yanbang Wang, Jon Kleinberg
To reconstruct hypergraph data, we start by analyzing hyperedge distributions in the projection, based on which we create a framework containing two modules: (1) to handle the enormous search space of potential hyperedges, we design a sampling strategy with efficacy guarantees that significantly narrows the space to a smaller set of candidates; (2) to identify hyperedges from the candidates, we further design a hyperedge classifier in two well-working variants that capture structural features in the projection.
3 code implementations • 28 Feb 2022 • Haoteng Yin, Muhan Zhang, Yanbang Wang, Jianguo Wang, Pan Li
Subgraph-based graph representation learning (SGRL) has been recently proposed to deal with some fundamental challenges encountered by canonical graph neural networks (GNNs), and has demonstrated advantages in many important data science applications such as link, relation and motif prediction.
Ranked #1 on Link Property Prediction on ogbl-citation2
no code implementations • ICLR 2021 • Yanbang Wang, Yen-Yu Chang, Yunyu Liu, Jure Leskovec, Pan Li
Temporal networks serve as abstractions of many real-world dynamic systems.
1 code implementation • 22 Nov 2020 • Haoteng Yin, Yanbang Wang, Pan Li
We want to explain how DE makes GNNs fit for node classification and link prediction.
2 code implementations • NeurIPS 2020 • Pan Li, Yanbang Wang, Hongwei Wang, Jure Leskovec
DE captures the distance between the node set whose representation is to be learned and each node in the graph.
no code implementations • 14 Dec 2018 • Yanbang Wang, Nancy Law, Erik Hemberg, Una-May O'Reilly
Student learning activity in MOOCs can be viewed from multiple perspectives.
no code implementations • 12 Dec 2018 • Mucong Ding, Yanbang Wang, Erik Hemberg, Una-May O'Reilly
It consists of two alternative transfer methods based on representation learning with auto-encoders: a passive approach using transductive principal component analysis and an active approach that uses a correlation alignment loss term.