no code implementations • 27 Dec 2023 • Lihui Liu, Blaine Hill, Boxin Du, Fei Wang, Hanghang Tong
CornNet adopts a teacher-student architecture where a teacher model learns question representations using human writing reformulations, and a student model to mimic the teacher model's output via reformulations generated by LLMs.
no code implementations • 6 Oct 2023 • Zhichen Zeng, Boxin Du, Si Zhang, Yinglong Xia, Zhining Liu, Hanghang Tong
To depict high-order relationships across multiple networks, the FGW distance is generalized to the multi-marginal setting, based on which networks can be aligned jointly.
no code implementations • 11 Apr 2023 • Boxin Du, Lihui Liu, Jiejun Xu, Fei Wang, Hanghang Tong
Graph Neural Networks (GNNs) have been widely applied on a variety of real-world applications, such as social recommendation.
no code implementations • 19 Jun 2022 • Boxin Du, Changhe Yuan, Fei Wang, Hanghang Tong
Despite the success of the Sylvester equation empowered methods on various graph mining applications, such as semi-supervised label learning and network alignment, there also exists several limitations.
no code implementations • 6 May 2022 • Beidi Zhao, Boxin Du, Zhe Xu, Liangyue Li, Hanghang Tong
Graph Neural Networks (GNNs) have achieved tremendous success in a variety of real-world applications by relying on the fixed graph data as input.
no code implementations • 5 May 2022 • Zhenning Zhang, Boxin Du, Hanghang Tong
Bundle recommendation is an emerging research direction in the recommender system with the focus on recommending customized bundles of items for users.
no code implementations • 23 May 2021 • Boxin Du, Changhe Yuan, Robert Barton, Tal Neiman, Hanghang Tong
Despite the prevalence of hypergraphs in a variety of high-impact applications, there are relatively few works on hypergraph representation learning, most of which primarily focus on hyperlink prediction, often restricted to the transductive learning setting.
no code implementations • 19 May 2021 • Zhe Xu, Boxin Du, Hanghang Tong
Generally speaking, the vast majority of the existing works aim to answer the following question, that is, given a graph, what is the best way to mine it?
no code implementations • 6 Nov 2020 • Lihui Liu, Boxin Du, Heng Ji, Hanghang Tong
In detail, we develop KompaRe, the first of its kind prototype system that provides comparative reasoning capability over large knowledge graphs.