Yuchen Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yuchen Yan has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Hanghang Tong
University of Illinois Urbana-Champaign, Urbana, IL, USA
10 shared publications - Yada Zhu
IBM Research, Yorktown Heights, NY, USA
4 shared publications - Baoyu Jing
University of Illinois at Urbana-Champaign
3 shared publications - Chanyoung Park
KAIST, Daejeon, Republic of Korea
2 shared publications - Chen Luo
Amazon Search, Palo Alto, CA, USA
2 shared publications - Dingsu Wang
University of Illinois at Urbana-Champaign, Urbana, IL, USA
2 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1673-1681
Which LLM to Fine-Tune? Agent-Driven Model Selection at Scale
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1673-1681
Open AccessWhich LLM to Fine-Tune? Agent-Driven Model Selection at Scale
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4790-4794
Building a Production Shopping Agent at Scale
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4790-4794
Open AccessBuilding a Production Shopping Agent at Scale
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 4960-4965
Few-Shot Knowledge Graph Completion via Transfer Knowledge from Similar Tasks
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 4960-4965
Open AccessFew-Shot Knowledge Graph Completion via Transfer Knowledge from Similar Tasks
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3708-3719
Fine-Grained Graph Rationalization
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3708-3719
Open AccessFine-Grained Graph Rationalization
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2064-2075
Joint Optimal Transport and Embedding for Network Alignment
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2064-2075
Open AccessJoint Optimal Transport and Embedding for Network Alignment
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2796-2806
Topological Anonymous Walk Embedding: A New Structural Node Embedding Approach
Network embedding is a commonly used technique in graph mining and plays an important role in a variety of applications. Most network embedding works can be categorized into positional node embedding methods and target at capturing the proximity/relative position of node pairs. Recently, structural node embedding has attracted tremendous research interest, which is intended to perceive the local structural information of node, i.e., nodes can share similar local structures in different positions of graphs. Although numerous structural node embedding methods are designed to encode such structural information, most, if not all, of these methods cannot simultaneously achieve the following three desired properties: (1) bijective mapping between embedding and local structure of node; (2) inductive capability; and (3) good interpretability of node embedding. To address this challenge, in this paper, we propose a novel structural node embedding algorithm named topological anonymous walk embedding (TAWE). Specifically, TAWE creatively integrates anonymous walk and breadth-first search (BFS) to construct the bijective mapping between node embedding and local structure of node. In addition, TAWE possesses inductive capability and good interpretability of node embedding. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of the proposed TAWE algorithm in both structural node classification task and structural node clustering task.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2796-2806
Open AccessTopological Anonymous Walk Embedding: A New Structural Node Embedding Approach
Network embedding is a commonly used technique in graph mining and plays an important role in a variety of applications. Most network embedding works can be categorized into positional node embedding methods and target at capturing the proximity/relative position of node pairs. Recently, structural node embedding has attracted tremendous research interest, which is intended to perceive the local structural information of node, i.e., nodes can share similar local structures in different positions of graphs. Although numerous structural node embedding methods are designed to encode such structural information, most, if not all, of these methods cannot simultaneously achieve the following three desired properties: (1) bijective mapping between embedding and local structure of node; (2) inductive capability; and (3) good interpretability of node embedding. To address this challenge, in this paper, we propose a novel structural node embedding algorithm named topological anonymous walk embedding (TAWE). Specifically, TAWE creatively integrates anonymous walk and breadth-first search (BFS) to construct the bijective mapping between node embedding and local structure of node. In addition, TAWE possesses inductive capability and good interpretability of node embedding. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of the proposed TAWE algorithm in both structural node classification task and structural node clustering task.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 2485-2496
PaCEr: Network Embedding From Positional to Structural
Network embedding plays an important role in a variety of social network applications. Existing network embedding methods, explicitly or implicitly, can be categorized into positional embedding (PE) methods or structural embedding (SE) methods. Specifically, PE methods encode the positional information and obtain similar embeddings for adjacent/close nodes, while SE methods aim to learn identical representations for nodes with the same local structural patterns, even if the two nodes are far away from each other. The disparate designs of the two types of methods lead to an apparent dilemma in that no embedding could perfectly capture both positional and structural information. In this paper, we seek to demystify the underlying relationship between positional embedding and structural embedding. We first point out that the positional embedding can produce the structural embedding with simple transformations, while the opposite direction cannot hold. Based on this finding, a novel network embedding model PACER is proposed, which optimizes the positional embedding with the help of random walk with restart (RWR) proximity distribution, and such positional embedding is then used to seamlessly obtain the structural embedding with simple transformations. Furthermore, two variants of PACER are proposed to handle node classification task on homophilic and heterophilic graphs. Extensive experiments on 17 datasets show that PACER achieves comparable or better performance than the state-of-the-arts.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 2485-2496
Open AccessPaCEr: Network Embedding From Positional to Structural
Network embedding plays an important role in a variety of social network applications. Existing network embedding methods, explicitly or implicitly, can be categorized into positional embedding (PE) methods or structural embedding (SE) methods. Specifically, PE methods encode the positional information and obtain similar embeddings for adjacent/close nodes, while SE methods aim to learn identical representations for nodes with the same local structural patterns, even if the two nodes are far away from each other. The disparate designs of the two types of methods lead to an apparent dilemma in that no embedding could perfectly capture both positional and structural information. In this paper, we seek to demystify the underlying relationship between positional embedding and structural embedding. We first point out that the positional embedding can produce the structural embedding with simple transformations, while the opposite direction cannot hold. Based on this finding, a novel network embedding model PACER is proposed, which optimizes the positional embedding with the help of random walk with restart (RWR) proximity distribution, and such positional embedding is then used to seamlessly obtain the structural embedding with simple transformations. Furthermore, two variants of PACER are proposed to handle node classification task on homophilic and heterophilic graphs. Extensive experiments on 17 datasets show that PACER achieves comparable or better performance than the state-of-the-arts.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (12) , 12976-12984
Sterling: Synergistic Representation Learning on Bipartite Graphs
A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs. Contrastive learning usually requires a large number of negative node pairs, which could lead to computational burden and semantic errors. In this paper, we introduce a novel synergistic representation learning model (STERLING) to learn node embeddings without negative node pairs. STERLING preserves the unique local and global synergies in bipartite graphs. The local synergies are captured by maximizing the similarity of the inter-type and intra-type positive node pairs, and the global synergies are captured by maximizing the mutual information of co-clusters. Theoretical analysis demonstrates that STERLING could improve the connectivity between different node types in the embedding space. Extensive empirical evaluation on various benchmark datasets and tasks demonstrates the effectiveness of STERLING for extracting node embeddings.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (12) , 12976-12984
Open AccessSterling: Synergistic Representation Learning on Bipartite Graphs
A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs. Contrastive learning usually requires a large number of negative node pairs, which could lead to computational burden and semantic errors. In this paper, we introduce a novel synergistic representation learning model (STERLING) to learn node embeddings without negative node pairs. STERLING preserves the unique local and global synergies in bipartite graphs. The local synergies are captured by maximizing the similarity of the inter-type and intra-type positive node pairs, and the global synergies are captured by maximizing the mutual information of co-clusters. Theoretical analysis demonstrates that STERLING could improve the connectivity between different node types in the embedding space. Extensive empirical evaluation on various benchmark datasets and tasks demonstrates the effectiveness of STERLING for extracting node embeddings.
- Open Access
STERLING: Synergistic Representation Learning on Bipartite Graphs
A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs. Contrastive learning usually requires a large number of negative node pairs, which could lead to computational burden and semantic errors. In this paper, we introduce a novel synergistic representation learning model (STERLING) to learn node embeddings without negative node pairs. STERLING preserves the unique local and global synergies in bipartite graphs. The local synergies are captured by maximizing the similarity of the inter-type and intra-type positive node pairs, and the global synergies are captured by maximizing the mutual information of co-clusters. Theoretical analysis demonstrates that STERLING could improve the connectivity between different node types in the embedding space. Extensive empirical evaluation on various benchmark datasets and tasks demonstrates the effectiveness of STERLING for extracting node embeddings.
Open AccessSTERLING: Synergistic Representation Learning on Bipartite Graphs
A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs. Contrastive learning usually requires a large number of negative node pairs, which could lead to computational burden and semantic errors. In this paper, we introduce a novel synergistic representation learning model (STERLING) to learn node embeddings without negative node pairs. STERLING preserves the unique local and global synergies in bipartite graphs. The local synergies are captured by maximizing the similarity of the inter-type and intra-type positive node pairs, and the global synergies are captured by maximizing the mutual information of co-clusters. Theoretical analysis demonstrates that STERLING could improve the connectivity between different node types in the embedding space. Extensive empirical evaluation on various benchmark datasets and tasks demonstrates the effectiveness of STERLING for extracting node embeddings.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the Acm Sigkdd Conference on Knowledge Discovery and Data Mining
- Vol. 2023, 2256-2268
Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
Multivariate time series (MTS) imputation is a widely studied problem in recent years. Existing methods can be divided into two main groups, including (1) deep recurrent or generative models that primarily focus on time series features, and (2) graph neural networks (GNNs) based models that utilize the topological information from the inherent graph structure of MTS as relational inductive bias for imputation. Nevertheless, these methods either neglect topological information or assume the graph structure is fixed and accurately known. Thus, they fail to fully utilize the graph dynamics for precise imputation in more challenging MTS data such as networked time series (NTS), where the underlying graph is constantly changing and might have missing edges. In this paper, we propose a novel approach to overcome these limitations. First, we define the problem of imputation over NTS which contains missing values in both node time series features and graph structures. Then, we design a new model named PoGeVon which leverages variational autoencoder (VAE) to predict missing values over both node time series features and graph structures. In particular, we propose a new node position embedding based on random walk with restart (RWR) in the encoder with provable higher expressive power compared with message-passing based graph neural networks (GNNs). We further design a decoder with 3-stage predictions from the perspective of multi-task learning to impute missing values in both time series and graph structures reciprocally. Experiment results demonstrate the effectiveness of our model over baselines.
- 4 August 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the Acm Sigkdd Conference on Knowledge Discovery and Data Mining
- Vol. 2023, 2256-2268
Open AccessNetworked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
Multivariate time series (MTS) imputation is a widely studied problem in recent years. Existing methods can be divided into two main groups, including (1) deep recurrent or generative models that primarily focus on time series features, and (2) graph neural networks (GNNs) based models that utilize the topological information from the inherent graph structure of MTS as relational inductive bias for imputation. Nevertheless, these methods either neglect topological information or assume the graph structure is fixed and accurately known. Thus, they fail to fully utilize the graph dynamics for precise imputation in more challenging MTS data such as networked time series (NTS), where the underlying graph is constantly changing and might have missing edges. In this paper, we propose a novel approach to overcome these limitations. First, we define the problem of imputation over NTS which contains missing values in both node time series features and graph structures. Then, we design a new model named PoGeVon which leverages variational autoencoder (VAE) to predict missing values over both node time series features and graph structures. In particular, we propose a new node position embedding based on random walk with restart (RWR) in the encoder with provable higher expressive power compared with message-passing based graph neural networks (GNNs). We further design a decoder with 3-stage predictions from the perspective of multi-task learning to impute missing values in both time series and graph structures reciprocally. Experiment results demonstrate the effectiveness of our model over baselines.