[Google Scholar] [ORCID] [ResearchGate] [Semantic Scholar]

Refereed Conference

1. Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting.
   Z. Wen and Y. Fang. Accepted by SIGIR 2023.
   [Paper] [Code] [Slides] [Poster]

2. Link Prediction on Latent Heterogeneous Graphs.
   K. Nguyen, Z. Liu and Y. Fang. Accepted by TheWebConf 2023.
   [Paper] [Code] [Slides] [Poster]

3. GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks.
   Z. Liu*, X. Yu*, Y. Fang and X. Zhang. Accepted by TheWebConf 2023.
   (* Co-first authors with equal contribution.)
   [Paper] [Code] [Slides] [Poster]

4. On Generalized Degree Fairness in Graph Neural Networks.
   Z. Liu, K. Nguyen and Y. Fang. Accepted by AAAI 2023.
   [Paper] [Code] [Slides] [Poster]

5. Learning to Count Isomorphisms with Graph Neural Networks.
   X. Yu*, Z. Liu*, Y. Fang and X. Zhang. Accepted by AAAI 2023.
   (* Co-first authors with equal contribution.)
   [Paper] [Code] [Slides] [Poster]

6. End-to-End Open-Set Semi-Supervised Node Classification with Out-of-Distribution Detection.
   T. Huang, D. Wang, Y. Fang and Z. Chen. In IJCAI 2022, pp. 2087--2093.
   [Paper] [Code] [Slides] [Poster]

7. TREND: TempoRal Event and Node Dynamics for Graph Representation Learning.
   Z. Wen and Y. Fang. In TheWebConf 2022, pp. 1159--1169.
   [Paper] [Code] [Slides]

8. On Size-Oriented Long-Tailed Graph Classification of Graph Neural Networks.
   Z. Liu, Q. Mao, C. Liu, Y. Fang and J. Sun. In TheWebConf 2022, 1506--1516.
   [Paper] [Code] [Slides]

9. Contrastive Pre-training of GNNs on Heterogeneous Graphs.
   X. Jiang, Y. Lu, Y. Fang and C. Shi. In CIKM 2021, pp. 803--812.
   [Paper] [Code] [Slides]

10. Topic-aware Heterogeneous Graph Neural Network for Link Prediction.
    S. Xu, C. Yang, C. Shi, Y. Fang, Y. Guo, T. Yang, L. Zhang and M. Hu. In CIKM 2021, pp. 2261--2270.
    [Paper] [Code] [Slides]

11. Dynamic Heterogeneous Graph Embedding via Heterogeneous Hawkes Process.
    Y. Ji, T. Jia, Y. Fang and C. Shi. In ECML-PKDD 2021 Part I, pp. 388--403.
    [Paper] [Code] [Slides]

12. Tail-GNN: Tail-Node Graph Neural Networks.
    Z. Liu, K. Nguyen and Y. Fang. In KDD 2021, pp. 1109--1119.
    [Paper] [Code] [Slides] [Poster]

13. Pre-training on Large-Scale Heterogeneous Graph.
    X. Jiang, T. Jia, C. Shi, Y. Fang, Z. Lin and H. Wang. In KDD 2021, pp. 756--766 .
    [Paper] [Code] [Slides] [Poster]

14. Node-wise Localization of Graph Neural Networks.
    Z. Liu, Y. Fang, C. Liu and S. C. H. Hoi. In IJCAI 2021, pp. 1520--1526.
    [Paper] [Supplementary] [Code] [Slides] [Poster]

15. Meta-Inductive Node Classification across Graphs.
    Z. Wen, Y. Fang and Z. Liu. In SIGIR 2021, pp. 1219--1228.
    [Paper] [Code] [Slides]

16. Learning to Pre-train Graph Neural Networks.
    Y. Lu, X. Jiang, Y. Fang and C. Shi. In AAAI 2021, pp. 4276--4284.
    [Paper] [Supplementary] [Code] [Slides] [Poster]

17. Relative and Absolute Location Embedding for Few-Shot Node Classification on Graph.
    Z. Liu, Y. Fang, C. Liu and S. C. H. Hoi. In AAAI 2021, pp. 4267--4275 .
    [Paper] [Supplementary] [Code] [Slides] [Poster]

18. Towards Locality-Aware Meta-Learning of Tail Node Embeddings on Networks.
    Z. Liu*, W. Zhang*, Y. Fang, X. Zhang and S. C. H. Hoi. In CIKM 2020, pp. 975--984.
    (* Co-first authors with equal contribution.)
    [Paper] [Code] [Slides]

19. TPR: Text-aware Preference Ranking for Recommender Systems.
    Y.-N. Chuang, C.-M. Chen, C.-J. Wang, M.-F. Tsai, Y. Fang and E. P. Lim. In CIKM 2020, pp. 215--224.
    [Paper] [Code] [Slides]

20. Adaptive Task Sampling for Meta-Learning.
    C. Liu*, Z. Wang*, D. Sahoo, Y. Fang, K. Zhang and S. C. H. Hoi. In ECCV 2020 Part XVIII, pp 752--769.
    (* Co-first authors with equal contribution.)
    [Paper] [Supplementary] [Code] [Slides]

21. Temporal Heterogeneous Interaction Graph Embedding For Next-Item Recommendation.
    Y. Ji, M. Yin, Y. Fang, H. Yang, X. Wang, T. Jia and C. Shi. In ECML-PKDD 2020 Part III, pp. 314--329.
    [Paper] [Code] [Slides]

22. Social Influence Attentive Neural Network for Friend-Enhanced Recommendation.
    Y. Lu, R. Xie, C. Shi, Y. Fang, W. Wang, X. Zhang and L. Lin. In ECML-PKDD 2020 Part IV (Applied Data Science), pp. 3--18.
    [Paper] [Code] [Slides] [中文概述] 

23. Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation.
    Y. Lu, Y. Fang and C. Shi. In KDD 2020, pp. 1563--1573.
    [Paper] [Code] [Slides] [Video] [Poster] [中文概述] 

24. BiANE: Bipartite Attributed Network Embedding.
    W. Huang, Y. Li, Y. Fang, J. Fan and H. Yang. In SIGIR 2020, pp. 149--158.
    [Paper] [Code] [Slides] [中文概述] 

25. Multiplex Memory Network for Collaborative Filtering.
    X. Jiang, B. Hu, Y. Fang and C. Shi. In SDM 2020, pp. 91--99.
    [Paper] [Supplementary] [Code] [中文概述] 

26. Correlation-Sensitive Next-Basket Recommendation.
    D.-T. Le, H. W. Lauw and Y. Fang. In IJCAI 2019, pp. 2808--2814.
    [Paper] [Code] [Slides] [Poster] 

27. Adversarial Learning on Heterogeneous Information Networks.
    B. Hu, Y. Fang and C. Shi. In KDD 2019, pp. 120--129.
    [Paper] [Code] [Poster] [中文概述] 

28. Heterogeneous Embedding Propagation for Large-scale E-Commerce User Alignment.
    V. W. Zheng, M. Sha, Y. Li, H. Yang, Y. Fang, Z. Zhang, K.-L. Tan and K. C.-C. Chang. In ICDM 2018 (Short), pp. 1434--1439.
    [Paper] [Slides] [Poster]

29. Modeling Contemporaneous Basket Sequences with Twin Networks for Next-Item Recommendation.
    D.-T. Le, H. W. Lauw and Y. Fang. In IJCAI 2018, pp. 3414--3420.
    [Paper] [Code] [Slides] [Poster]

30. Region Average Pooling for Context-Aware Object Detection.
    K. Kuan, G. Manek, J. Lin, Y. Fang and V. Chandrasekhar. In ICIP 2017, pp. 1347--1351.
    [Paper]

31. Object Detection Meets Knowledge Graphs.
    Y. Fang, K. Kuan, J. Lin, C. Tan and V. Chandrasekhar. In IJCAI 2017, pp. 1661--1667.
    [Paper] [Code] [Slides] [Poster]

32. Basket-Sensitive Personalized Item Recommendation.
    D.-T. Le,  H. W. Lauw and Y. Fang. In IJCAI 2017, pp. 2060--2066.
    [Paper] [Slides] [Poster]

33. Modeling Sequential Preferences with Dynamic User and Context Factors.
    D.-T. Le, Y. Fang and H. W. Lauw. In ECML-PKDD 2016, pp. 145--161.
    [Paper] [Supplementary] [Slides] [Poster]

34. Learning to Query: Focused Web Page Harvesting for Entity Aspects.
    Y. Fang, V. W. Zheng and K. C.-C. Chang. In ICDE 2016, pp. 1002--1013.
    [Paper] [Slides] [Poster]

35. Semantic Proximity Search on Graphs with Metagraph-based Learning.
    Y. Fang, W. Lin, V. W. Zheng, M. Wu, K. C.-C. Chang and X. Li. In ICDE 2016, pp. 277--288.
    [Paper] [Code] [Slides] [Poster]

36. Graph-based Semi-supervised Learning: Realizing Pointwise Smoothness Probabilistically.
    Y. Fang, K. C.-C. Chang and H. W. Lauw. In ICML 2014 (2), pp. 406--414.
    [Paper] [Supplementary] [Data] [Slides] 

37. Incremental and Accuracy-Aware Personalized PageRank through Scheduled Approximation.
    F. Zhu, Y. Fang, K. C.-C. Chang and J. Ying. In VLDB 2013, 6(6), pp. 481--492.
    Extended version invited to the collection of Best Papers of VLDB'13.
    [Paper] [Data] [Slides] 

38. RoundTripRank: Graph-based Proximity with Importance and Specificity.
    Y. Fang, K. C.-C. Chang and H. W. Lauw. In ICDE 2013, pp. 613--624.
    [Paper] [Data] [Slides] [Poster] 

39. Confidence-Aware Graph Regularization with Heterogeneous Pairwise Features.
    Y. Fang, P. Hsu and K. C.-C. Chang. In SIGIR 2012, pp. 951--960.
    [Paper] [Slides] 

40. Searching Patterns for Relation Extraction over the Web: Rediscovering the Pattern-Relation Duality.
    Y. Fang and K. C.-C. Chang. In WSDM 2011, pp. 825--834.
    [Paper] [Poster] 

41. Privacy beyond Single Sensitive Attribute.
    Y. Fang, M. Ashrafi and S.-K. Ng. In DEXA 2011, pp. 187--201.
    [PDF] 

42. Efficient Skyline Maintenance for Streaming Data with Partially-Ordered Domains.
    Y. Fang and C. Y. Chan. In DASFAA 2010, pp. 322--336.
    [Paper] [Slides]

Refereed Journal 

1. Dual-View Preference Learning for Adaptive Recommendation.
   Z. Liu, Y. Fang*, M. Wu*. To appear in IEEE TKDE.
   (* Corresponding author.)
   [Paper] [Code]

2. Mitigating Popularity Bias for Users and Items with Fairness-centric Adaptive Recommendation.
   Z. Liu, Y. Fang*, M. Wu*. In ACM TOIS  41(3), Article No. 55, 2023.
   (* Corresponding author.)
   [Paper] [Code]

3. Pre-training Graph Neural Networks for Link Prediction in Biomedical Networks.
   Y. Long, M. Wu, Y. Liu, Y. Fang, C.-K. Kwoh, J. Chen, J. Luo and X.-L. Li. In Bioinformatics 38(8), 2022, pp. 2254--2262.
   [Paper] [Supplementary] [Code] 

4. Unified and Incremental SimRank: Index-free Approximation with Scheduled Principle.
   F. Zhu, Y. Fang, K. Zhang, K. C.-C. Chang, H. Cao, Z. Jiang, M. Wu. In IEEE TKDE 35(3), 2023, pp. 3195--3210.
   [Paper] [Code] 

5. Neighbor-Anchoring Adversarial Graph Neural Networks.
   Z. Liu, Y. Fang*, Y. Liu, V. W. Zheng. In IEEE TKDE 35(1), 2023, pp. 784--795. 
   (* Corresponding author.)
   [Paper] [Code] 

6. Prediction of Synthetic Lethal Interactions in Human Cancers using Multi-view Graph Auto-Encoder.
   Z. Hao, D. Wu, Y. Fang*, M. Wu*, R. Cai* and Xiao-Li Li. In IEEE J. of Biomedical & Health Informatics (JBHI) 25(10), 2021, pp.  4041--4051.
   (* Co-corresponding authors.)
   [Paper] [Supplementary] [Code]

7. Multi-View Collaborative Network Embedding.
   S. Ata, Y. Fang*, M. Wu*, J. Shi, C. Kwoh, X. Li. In ACM TKDD 15(3), Article No. 39, 2021.
   (* Co-corresponding authors.)
   [Paper] [Code] 

8. Recent Advances in Network-based Methods for Disease Gene Prediction.
   S. Ata, M. Wu, Y. Fang, L. Ou-Yang, C. Kwoh and X. Li. In Briefings in Bioinformatics 22(4), Article No. bbaa303, 2020.
   [Paper] [Code] 

9. Accelerating Large-Scale Heterogeneous Interaction Graph Embedding Learning via Importance Sampling.
   Y. Ji, M. Yin, H. Yang, J. Zhou, V. W. Zheng, C. Shi* and Y. Fang*. In ACM TKDD 15(1), Article No.10, 2020.
   (* Co-corresponding authors.)
   [Paper] [Code]

10. Semi-supervised Co-Clustering on Attributed Heterogeneous Information Networks.
    Y. Ji, C. Shi, Y. Fang, X. Kong and M. Yin. In IPM 57(6), 2020.
    [Paper] [Code] 

11. mg2vec: Learning Relationship-Preserving Heterogeneous Graph Representations via Metagraph Embedding.
    W. Zhang, Y. Fang*, Z. Liu, M. Wu and X. Zhang*. In IEEE TKDE 34(3), 2020, pp. 1317--1329.
    (* Co-corresponding authors.)
    [Paper] [Code] 

12. Dual-Dropout Graph Convolutional Network for Predicting Synthetic Lethality in Human Cancers.
    R. Cai, X. Chen, Y. Fang*, M. Wu* and Y. Hao. In Bioinformatics 36(16), 2020, pp. 4458--4465.
    (* Co-corresponding authors.)
    [Paper] [Code] [Supplementary] 

13. Metagraph-based Learning on Heterogeneous Graphs.
    Y. Fang, W. Lin, V. W. Zheng, M. Wu, J. Shi, K. C.-C. Chang and X. Li. In IEEE TKDE 33(1), 2019, pp. 154--168.
    [Paper] [Code]

14. Integrating Node Embeddings and Biological Annotations for Genes to Predict Disease-Gene Associations.
    S. Ata, L. Ou-Yang, Y. Fang, C.-K. Kwoh, M. Wu and X. Li. In BMC Systems Biology 12(Supp 9), 2018, pp. 31--44.
    Invited for oral presentation at GIW'18.
    [Paper]

15. Disease Gene Classification with Metagraph Representations.
    S. Ata, Y. Fang, M. Wu, X. Xiao and X. Li. In Methods 131, 2017, pp. 83--92.
    [Paper] 

16. Scheduled Approximation for Personalized PageRank with Utility-Driven Hub Selection.
    F. Zhu, Y. Fang, K. C.-C. Chang and J. Ying. In VLDBJ 24(5), 2015, Special Issue on Best Papers of VLDB'13, pp. 655--679.
    [Paper] [Data] 

17. Entity Linking on Microblogs with Spatial and Temporal Signals.
    Y. Fang and M.-W. Chang. In TACL 2(Oct), 2014, pp. 259--272.
    Invited for oral presentation at EMNLP'14. 
    [Paper] [Slides] [Data] 

Refereed Workshop/Demo/Abstract 

1. Unified and Incremental SimRank: Index-free Approximation with Scheduled Principle (Extended Abstract).
   F. Zhu, Y. Fang, K. Zhang, K. C.-C. Chang, H. Cao, Z. Jiang, M. Wu. In ICDE 2022, pp. 1569--1570.
   [Extended abstract] [Poster]

2. Neighbor-Anchoring Adversarial Graph Neural Networks (Extended Abstract).
   Z. Liu, Y. Fang, Y. Liu, V. W. Zheng. To appear in ICDE 2022, pp. 1571--1572.
   [Extended abstract] [Poster]

3. Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation. [Abstract only].
   Y. Lu, Y. Fang, C. Shi. In China National Conference on Social Media Processing (SMP) 2020.
   [Abstract]

4. Network Embedding with Attribute Refinement. [Workshop paper]
   T. Xiao, Y. Fang, H. Yang and V. W. Zheng. In KDD Workshop on Mining and Learning with Graphs 2017 (non-archival).
   [Paper] [Video]

5. Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text. [Workshop paper]
   Z. Wang*, K. Kuan*, M. Ravaut*, G. Manek*, S. Song*, Y. Fang, et al. In CVPR Workshop on YouTube-8M Challenge 2017 (non-archival).
   (* Co-first authors with equal contribution.)
   Ranked 22/655 in the corresponding Kaggle challenge.
   [Paper] 

6. ARISE-PIE: A People Information Integration Engine over the Web. [Workshop paper]
   V. W. Zheng, T. Hoang, P. Chen, Y. Fang, X. Yang and K. C.-C. Chang. In CIKM Workshop on Data-Driven Talent Acquisition 2016 (non-archival).
   [Paper] [Demo] 

7. IntelligShop: Enabling Intelligent Shopping in Malls through Location-based Augmented Reality. [Demo paper]
   A. Adhikari, V. W. Zheng, H. Cao, M. Lin, Y. Fang and K. C.-C. Chang. In ICDM 2015, pp. (W)1604--1607.
   Featured in media coverage in the United States.
   [Paper] [Demo] [News]  

8. Differences in Plasma Lipids during Rested Wakefulness and Sleep Deprivation. [Abstract only]
   S. Huang, E. C.-P. Chua, G. Shui, Y. Fang, S.-C. Yeo, M. R. Wenk and J. J. Gooley. In SLEEP 2015.
   [Abstract] [Poster] 

Editorial 

1. The 4th Workshop on Heterogeneous Information Network Analysis and Applications (HENA 2021).
   C. Shi, Y. Fang , Y. Ye , J. Zhang. In KDD 2021, pp. 4157--4158.
   [PDF]

Book Chapter 

2. Disease Gene Classification with Metagraph Representations.
   S. Ata, Y. Fang, M. Wu, X. Li and X. Xiao. In Data Mining for Systems Biology: Methods and Protocols, 2nd Edition, 2018, pp. 211--224. Humana Press, New York, NY.
   [Link] 

Preprint 

1. End-to-End Video Classification with Knowledge Graphs.
   Y. Fang, Zhe Wang, Jie Lin, Luis Fernando D’Haro, Kim Jung Jae, Zeng Zeng and Vijay Chandrasekhar. In arXiv:1711.01714 [cs.CV].
   [PDF] 

Dissertation 

1. Walking Forward and Backward: Towards Graph-based Searching and Mining.
   Y. Fang. PhD Dissertation, University of Illinois at Urbana-Champaign, 2014.
   [PDF] 

2. Finding Skyline Objects in Streaming Data.
   Y. Fang. Honors Year Dissertation, National University of Singapore, 2009.
   [PDF]