Xixun Lin

Xixun Lin

Auto-generated profile, based on publicly available information

Xixun Lin

Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
15 March 2025 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
XLXixun Lin
Xixun Lin
RLRui Liu
Rui Liu
YCYanan Cao
Yanan Cao
LZLixin Zou
Lixin Zou
QLQing Li
Qing Li
GXGuandong Xu
Guandong Xu
Multimodal recommendation, which utilizes rich multimodal information to learn user preferences, has attracted significant attention. Most works focus on designing powerful encoders for extracting multimodal features, and simply aggregate the learned features together to make prediction. Consequently, they have a limited capacity to learn the inter-modality knowledge including the modality-shared and modality-unique knowledge. In fact, learning the modality-shared knowledge enables us to align cross-modality data for fusing heterogeneous modality features. Learning the modality-unique knowledge is equally important when recommendation tasks only involve a small amount of shared features and the necessary information is contained within specific modality. In this article, we propose Contrastive Modality-Disentangled Learning (CMDL) to overcome this critical limitation. CMDL exactly captures the inter-modality knowledge by achieving modality disentanglement. Specifically, CMDL first disentangles the initial representation into the modality-invariant and modality-specific representations. Afterwards, CMDL introduces a novel manner of contrastive learning to approximate the MI upper bounds for achieving disentanglement regularization. Building upon the proposed regularization, CMDL encourages the modality-invariant and modality-specific representations to capture the modality-shared and modality-unique knowledge respectively and to be statistically independent to each other. Empirically, extensive experiments are conducted on benchmark datasets, demonstrating the superior performance of CMDL compared with strong multimodal recommenders.

26 March 2025 in Neural Networks
Verified
Journal Article
Closed access
YCYanan Cao
Yanan Cao
FSFengzhao Shi
Fengzhao Shi
QYQing Yu
Qing Yu
XLXixun Lin
Xixun Lin
CZChuan Zhou
Chuan Zhou
DYDawei Yin
Dawei Yin

23 August 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
XLXixun Lin
Xixun Lin
CZChuan Zhou
Chuan Zhou
Jia WUJia WU
Jia WU
LZLixin Zou
Lixin Zou
SPShirui Pan
Shirui Pan
DYDawei Yin
Dawei Yin
Recommender systems have been widely adopted in various online personal e-commerce applications for improving user experience. A long-standing challenge in recommender systems is how to provide accurate recommendation to users in cold-start situations where only a few user-item interactions can be observed. Recently, meta learning methods provide a promising solution, and most of them follow a way of parameter initialization where predictions can be fast adapted via multiple gradient descent steps. While these meta-learning recommenders promote model performance, how to derive a fundamental paradigm that enables both flexible approximations of complex user interaction distributions and effective task adaptations of global knowledge still remains a critical yet under-explored problem. To this end, we present the F low-based A daptive N eural P rocess (FANP), a new probabilistic meta-learning model where estimating the preference of each user is governed by an underlying stochastic process. Following an encoder-decoder generative framework, FANP is an effective few-shot function estimator that directly maps limited user interactions to a predictive distribution without complicated gradient updates. Through introducing a conditional normalization flow-based encoder, FANP can get rid of the model bias on latent variables and thereby derive more flexible variational distributions. Meanwhile, we propose a task-adaptive mechanism capturing the relevance of different tasks for improving adaptation ability of global knowledge. The learned task-specific and task-relevant representations are simultaneously exploited to generate the decoder parameters via a novel modulation-augmented hypernetwork. FANP is evaluated on both scenario-specific and user-specific cold-start recommendations on various real-world datasets. Extensive experimental results and detailed model analyses demonstrate that our model yields superior performance compared with multiple state-of-the-art meta-learning recommenders.

22 April 2025
Verified
Conference Paper
Open access
XLXixun Lin
Xixun Lin
YCYanan Cao
Yanan Cao
NSNan Sun
Nan Sun
LZLixin Zou
Lixin Zou
CZChuan Zhou
Chuan Zhou
Jia WUJia WU
Jia WU

3 August 2025
Verified
Conference Paper
Open access
YWYongxuan Wu
Yongxuan Wu
YLYang Liu
Yang Liu
XLXixun Lin
Xixun Lin
HZHong Zhou
Hong Zhou
YCYanan Cao
Yanan Cao
YLYanbing Liu
Yanbing Liu

3 August 2025
Verified
Conference Paper
Open access
SZShichao Zhu
Shichao Zhu
MLMufan Li
Mufan Li
GPGuangmou Pan
Guangmou Pan
XLXixun Lin
Xixun Lin