Search Results for author: Yunsheng Bai

Found 11 papers, 4 papers with code

Dual-Geometric Space Embedding Model for Two-View Knowledge Graphs

1 code implementation19 Sep 2022 Roshni G. Iyer, Yunsheng Bai, Wei Wang, Yizhou Sun

For works that seek to put both views of the KG together, the instance and ontology views are assumed to belong to the same geometric space, such as all nodes embedded in the same Euclidean space or non-Euclidean product space, an assumption no longer reasonable for two-view KGs where different portions of the graph exhibit different structures.

Knowledge Graphs

Subgraph Matching via Query-Conditioned Subgraph Matching Neural Networks and Bi-Level Tree Search

no code implementations21 Jul 2022 Yunsheng Bai, Derek Xu, Yizhou Sun, Wei Wang

In this paper, we propose N-BLS with two innovations to tackle the challenges: (1) A novel encoder-decoder neural network architecture to dynamically compute the matching information between the query and the target graphs at each search state; (2) A Monte Carlo Tree Search enhanced bi-level search framework for training the policy and value networks.


Enabling Automated FPGA Accelerator Optimization Using Graph Neural Networks

no code implementations17 Nov 2021 Atefeh Sohrabizadeh, Yunsheng Bai, Yizhou Sun, Jason Cong

High-level synthesis (HLS) has freed the computer architects from developing their designs in a very low-level language and needing to exactly specify how the data should be transferred in register-level.

Learning to Search for Fast Maximum Common Subgraph Detection

no code implementations1 Jan 2021 Yunsheng Bai, Derek Qiang Xu, Yizhou Sun, Wei Wang

Detecting the Maximum Common Subgraph (MCS) between two input graphs is fundamental for applications in biomedical analysis, malware detection, cloud computing, etc.

Graph Matching Imitation Learning +1

Bi-Level Graph Neural Networks for Drug-Drug Interaction Prediction

no code implementations11 Jun 2020 Yunsheng Bai, Ken Gu, Yizhou Sun, Wei Wang

We introduce Bi-GNN for modeling biological link prediction tasks such as drug-drug interaction (DDI) and protein-protein interaction (PPI).

Link Prediction

GLSearch: Maximum Common Subgraph Detection via Learning to Search

no code implementations8 Feb 2020 Yunsheng Bai, Derek Xu, Yizhou Sun, Wei Wang

However, MCS computation is NP-hard, and state-of-the-art MCS solvers rely on heuristic search algorithms which in practice cannot find good solution for large graph pairs given a limited computation budget.

Graph Embedding Graph Matching +3

Neural Maximum Common Subgraph Detection with Guided Subgraph Extraction

no code implementations25 Sep 2019 Yunsheng Bai, Derek Xu, Ken Gu, Xueqing Wu, Agustin Marinovic, Christopher Ro, Yizhou Sun, Wei Wang

Maximum Common Subgraph (MCS) is defined as the largest subgraph that is commonly present in both graphs of a graph pair.

Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity

1 code implementation1 Apr 2019 Yunsheng Bai, Hao Ding, Yang Qiao, Agustin Marinovic, Ken Gu, Ting Chen, Yizhou Sun, Wei Wang

We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity.

General Classification Graph Classification +2

Convolutional Set Matching for Graph Similarity

no code implementations23 Oct 2018 Yunsheng Bai, Hao Ding, Yizhou Sun, Wei Wang

We introduce GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs.

Graph Similarity set matching

Learning-based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching

1 code implementation10 Sep 2018 Yunsheng Bai, Hao Ding, Yizhou Sun, Wei Wang

Since computing the exact distance/similarity between two graphs is typically NP-hard, a series of approximate methods have been proposed with a trade-off between accuracy and speed.

Combinatorial Optimization Graph Classification +4

Cannot find the paper you are looking for? You can Submit a new open access paper.