Yijun Tian

Mr. Yijun Tian


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YTYijun Tian
Yijun Tian
KDKaiwen Dong
Kaiwen Dong
CZChunhui Zhang
Chunhui Zhang
CZChuxu Zhang
Chuxu Zhang
Nitesh ChawlaNitesh Chawla
Nitesh Chawla
Generative self-supervised learning (SSL), especially masked autoencoders, has become one of the most exciting learning paradigms and has shown great potential in handling graph data. However, real-world graphs are always heterogeneous, which poses three critical challenges that existing methods ignore: 1) how to capture complex graph structure? 2) how to incorporate various node attributes? and 3) how to encode different node positions? In light of this, we study the problem of generative SSL on heterogeneous graphs and propose HGMAE, a novel heterogeneous graph masked autoencoder model to address these challenges. HGMAE captures comprehensive graph information via two innovative masking techniques and three unique training strategies. In particular, we first develop metapath masking and adaptive attribute masking with dynamic mask rate to enable effective and stable learning on heterogeneous graphs. We then design several training strategies including metapath-based edge reconstruction to adopt complex structural information, target attribute restoration to incorporate various node attributes, and positional feature prediction to encode node positional information. Extensive experiments demonstrate that HGMAE outperforms both contrastive and generative state-of-the-art baselines on several tasks across multiple datasets. Codes are available at https://github.com/meettyj/HGMAE.

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YTYijun Tian
Yijun Tian
HSHuan Song
Huan Song
ZWZichen Wang
Zichen Wang
HWHaozhu Wang
Haozhu Wang
ZHZiqing Hu
Ziqing Hu
PXPanpan Xu
Panpan Xu
Large language models (LLMs) have shown remarkable generalization capability with exceptional performance in various language modeling tasks. However, they still exhibit inherent limitations in precisely capturing and returning grounded knowledge. While existing work has explored utilizing knowledge graphs (KGs) to enhance language modeling via joint training and customized model architectures, applying this to LLMs is problematic owing to their large number of parameters and high computational cost. Therefore, how to enhance pre-trained LLMs using grounded knowledge, e.g., retrieval-augmented generation, remains an open question. In this work, we propose Graph Neural Prompting (GNP), a novel plug-and-play method to assist pre-trained LLMs in learning beneficial knowledge from KGs. GNP encompasses various designs, including a standard graph neural network encoder, a cross-modality pooling module, a domain projector, and a self-supervised link prediction objective. Extensive experiments on multiple datasets demonstrate the superiority of GNP on both commonsense and biomedical reasoning tasks across different LLM sizes and settings. Code is available at https://github.com/meettyj/GNP.

1 January 2024
Verified
Conference Paper
Open access
PDF file
ZLZheyuan Liu
Zheyuan Liu
GDGuangyao Dou
Guangyao Dou
ZTZhaoxuan Tan
Zhaoxuan Tan
YTYijun Tian
Yijun Tian
MJMeng Jiang
Meng Jiang
Zheyuan Liu, Guangyao Dou, Zhaoxuan Tan, Yijun Tian, Meng Jiang. Findings of the Association for Computational Linguistics ACL 2024. 2024.

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZGZhichun Guo
Zhichun Guo
CZChunhui Zhang
Chunhui Zhang
YFYujie Fan
Yujie Fan
YTYijun Tian
Yijun Tian
CZChuxu Zhang
Chuxu Zhang
Nitesh ChawlaNitesh Chawla
Nitesh Chawla
Graph neural networks (GNNs) have shown remarkable performance on diverse graph mining tasks. While sharing the same message passing framework, our study shows that different GNNs learn distinct knowledge from the same graph. This implies potential performance improvement by distilling the complementary knowledge from multiple models. However, knowledge distillation (KD) transfers knowledge from high-capacity teachers to a lightweight student, which deviates from our scenario: GNNs are often shallow. To transfer knowledge effectively, we need to tackle two challenges: how to transfer knowledge from compact teachers to a student with the same capacity; and, how to exploit student GNN's own learning ability. In this paper, we propose a novel adaptive KD framework, called BGNN, which sequentially transfers knowledge from multiple GNNs into a student GNN. We also introduce an adaptive temperature module and a weight boosting module. These modules guide the student to the appropriate knowledge for effective learning. Extensive experiments have demonstrated the effectiveness of BGNN. In particular, we achieve up to 3.05% improvement for node classification and 6.35% improvement for graph classification over vanilla GNNs.

1 August 2023
Verified
Conference Paper
Open access
PDF file
ZKZiyi Kou
Ziyi Kou
SPShichao Pei
Shichao Pei
YTYijun Tian
Yijun Tian
XZXiangliang Zhang
Xiangliang Zhang
In this paper, we study a controllable prompt adversarial attacking problem for text guided image generation (Text2Image) models in the black-box scenario, where the goal is to attack specific visual subjects (e.g., changing a brown dog to white) in a generated image by slightly, if not imperceptibly, perturbing the characters of the driven prompt (e.g., ``brown'' to ``br0wn''). Our study is motivated by the limitations of current Text2Image attacking approaches that still rely on manual trials to create adversarial prompts. To address such limitations, we develop CharGrad, a character-level gradient based attacking framework that replaces specific characters of a prompt with pixel-level similar ones by interactively learning the perturbation direction for the prompt and updating the attacking examiner for the generated image based on a novel proxy perturbation representation for characters. We evaluate CharGrad using the texts from two public image captioning datasets. Results demonstrate that CharGrad outperforms existing text adversarial attacking approaches on attacking various subjects of generated images by black-box Text2Image models in a more effective and efficient way with less perturbation on the characters of the prompts.

22 February 2024 in arXiv
Verified
Preprint
Open access
PDF file
LWLirong Wu
Lirong Wu
YTYijun Tian
Yijun Tian
YHYufei Huang
Yufei Huang
SLSiyuan Li
Siyuan Li
HLHaitao Lin
Haitao Lin
SLStan Z. Li
Stan Z. Li
Protein-Protein Interactions (PPIs) are fundamental in various biological processes and play a key role in life activities. The growing demand and cost of experimental PPI assays require computational methods for efficient PPI prediction. While existing methods rely heavily on protein sequence for PPI prediction, it is the protein structure that is the key to determine the interactions. To take both protein modalities into account, we define the microenvironment of an amino acid residue by its sequence and structural contexts, which describe the surrounding chemical properties and geometric features. In addition, microenvironments defined in previous work are largely based on experimentally assayed physicochemical properties, for which the "vocabulary" is usually extremely small. This makes it difficult to cover the diversity and complexity of microenvironments. In this paper, we propose Microenvironment-Aware Protein Embedding for PPI prediction (MPAE-PPI), which encodes microenvironments into chemically meaningful discrete codes via a sufficiently large microenvironment "vocabulary" (i.e., codebook). Moreover, we propose a novel pre-training strategy, namely Masked Codebook Modeling (MCM), to capture the dependencies between different microenvironments by randomly masking the codebook and reconstructing the input. With the learned microenvironment codebook, we can reuse it as an off-the-shelf tool to efficiently and effectively encode proteins of different sizes and functions for large-scale PPI prediction. Extensive experiments show that MAPE-PPI can scale to PPI prediction with millions of PPIs with superior trade-offs between effectiveness and computational efficiency than the state-of-the-art competitors.