Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- abstractMarch 2024
Profiling Urban Mobility Patterns with High Spatial and Temporal Resolution: A Deep Dive into Cellphone Geo-position Data
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 1196–1197https://doi.org/10.1145/3616855.3636504Traditionally, urban traveling patterns have been obtained through origin-destination surveys. This method presents drawbacks such as high costs, limited representativeness of the surveyed population, and low spatial and temporal resolution of the ...
- research-articleMarch 2024
Global Heterogeneous Graph and Target Interest Denoising for Multi-behavior Sequential Recommendation
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 387–395https://doi.org/10.1145/3616855.3635857Multi-behavior sequential recommendation (MBSR) predicts a user's next item of interest based on their interaction history across different behavior types. Although existing studies have proposed capturing the correlation between different types of ...
- research-articleMarch 2024
LLMRec: Large Language Models with Graph Augmentation for Recommendation
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 806–815https://doi.org/10.1145/3616855.3635853The problem of data sparsity has long been a challenge in recommendation systems, and previous studies have attempted to address this issue by incorporating side information. However, this approach often introduces side effects such as noise, ...
- research-articleMarch 2024
ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 452–461https://doi.org/10.1145/3616855.3635845Personalized content-based recommender systems have become indispensable tools for users to navigate through the vast amount of content available on platforms like daily news websites and book recommendation services. However, existing recommenders face ...
- research-articleMarch 2024
Rethinking and Simplifying Bootstrapped Graph Latents
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 665–673https://doi.org/10.1145/3616855.3635842Graph contrastive learning (GCL) has emerged as a representative paradigm in graph self-supervised learning, where negative samples are commonly regarded as the key to preventing model collapse and producing distinguishable representations. Recent ...
-
- research-articleMarch 2024
Cost-Effective Active Learning for Bid Exploration in Online Advertising
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 788–796https://doi.org/10.1145/3616855.3635839As a bid optimization algorithm in the first-price auction (FPA), bid shading is used in online advertising to avoid overpaying for advertisers. However, we find the bid shading approach would incur serious local optima. This effect prevents the ...
- research-articleMarch 2024
From Second to First: Mixed Censored Multi-Task Learning for Winning Price Prediction
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 295–303https://doi.org/10.1145/3616855.3635838A transformation from second-price auctions (SPA) to first-price auctions (FPA) has been observed in online advertising. The consequential coexistence of mixed FPA and SPA auction types has further led to the problem of mixed censorship, making bid ...
- research-articleMarch 2024
MAD: Multi-Scale Anomaly Detection in Link Streams
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 38–46https://doi.org/10.1145/3616855.3635834Given an arbitrary group of computers, how to identify abnormal changes in their communication pattern? How to assess if the absence of some communications is normal or due to a failure? How to distinguish local from global events when communication data ...
- research-articleMarch 2024
Continuous-time Autoencoders for Regular and Irregular Time Series Imputation
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 826–835https://doi.org/10.1145/3616855.3635831Time series imputation is one of the most fundamental tasks for time series. Real-world time series datasets are frequently incomplete (or irregular with missing observations), in which case imputation is strongly required. Many different time series ...
- research-articleMarch 2024
User Consented Federated Recommender System Against Personalized Attribute Inference Attack
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 276–285https://doi.org/10.1145/3616855.3635830Recommender systems can be privacy-sensitive. To protect users' private historical interactions, federated learning has been proposed in distributed learning for user representations. Using federated recommender (FedRec) systems, users can train a shared ...
- research-articleMarch 2024
MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 1032–1041https://doi.org/10.1145/3616855.3635820Traffic forecasting is a complex multivariate time-series regression task of paramount importance for traffic management and planning. However, existing approaches often struggle to model complex multi-range dependencies using local spatiotemporal ...
- research-articleMarch 2024
LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 28–37https://doi.org/10.1145/3616855.3635816Short video recommendations often face limitations due to the quality of user feedback, which may not accurately depict user interests. To tackle this challenge, a new task has emerged: generating more dependable labels from original feedback. Existing ...
- research-articleMarch 2024
C²DR: Robust Cross-Domain Recommendation based on Causal Disentanglement
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 341–349https://doi.org/10.1145/3616855.3635809Cross-domain recommendation aims to leverage heterogeneous information to transfers knowledge from a data-sufficient domain (source domain) to a data-scarce domain (target domain). Existing approaches mainly focus on learning single-domain user ...
- research-articleMarch 2024
Dynamic Sparse Learning: A Novel Paradigm for Efficient Recommendation
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 740–749https://doi.org/10.1145/3616855.3635780In the realm of deep learning-based recommendation systems, the increasing computational demands, driven by the growing number of users and items, pose a significant challenge to practical deployment. This challenge is primarily twofold: reducing the ...
- research-articleMarch 2024
GAP: A Grammar and Position-Aware Framework for Efficient Recognition of Multi-Line Mathematical Formulas
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 901–910https://doi.org/10.1145/3616855.3635776Formula recognition endeavors to automatically identify mathematical formulas from images. Currently, the Encoder-Decoder model has significantly advanced the translation from image to corresponding formula markups. Nonetheless, previous research ...
- research-articleMarch 2024
Intent Contrastive Learning with Cross Subsequences for Sequential Recommendation
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 548–556https://doi.org/10.1145/3616855.3635773The user purchase behaviors are mainly influenced by their intentions (e.g., buying clothes for decoration, buying brushes for painting, etc.). Modeling a user's latent intention can significantly improve the performance of recommendations. Previous ...
- research-articleMarch 2024
K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization
- Cheng Deng,
- Tianhang Zhang,
- Zhongmou He,
- Qiyuan Chen,
- Yuanyuan Shi,
- Yi Xu,
- Luoyi Fu,
- Weinan Zhang,
- Xinbing Wang,
- Chenghu Zhou,
- Zhouhan Lin,
- Junxian He
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 161–170https://doi.org/10.1145/3616855.3635772Large language models (LLMs) have achieved great success in general domains of natural language processing. In this paper, we bring LLMs to the realm of geoscience with the objective of advancing research and applications in this field. To this end, we ...
- research-articleMarch 2024
Incomplete Graph Learning via Attribute-Structure Decoupled Variational Auto-Encoder
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 304–312https://doi.org/10.1145/3616855.3635769Graph Neural Networks (GNNs) conventionally operate under the assumption that node attributes are entirely observable. Their performance notably deteriorates when confronted with incomplete graphs due to the inherent message-passing mechanisms. Current ...
- research-articleMarch 2024
Capturing Temporal Node Evolution via Self-supervised Learning: A New Perspective on Dynamic Graph Learning
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 443–451https://doi.org/10.1145/3616855.3635765\beginabstract Dynamic graphs play an important role in many fields like social relationship analysis, recommender systems and medical science, as graphs evolve over time. It is fundamental to capture the evolution patterns for dynamic graphs. Existing ...
- research-articleMarch 2024
CityCAN: Causal Attention Network for Citywide Spatio-Temporal Forecasting
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 702–711https://doi.org/10.1145/3616855.3635764Citywide spatio-temporal (ST) forecasting is a fundamental task for many urban applications, including traffic accident prediction, taxi demand planning, and crowd flow forecasting. The goal of this task is to generate accurate predictions concurrently ...