Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMay 2024
Item-side Fairness of Large Language Model-based Recommendation System
WWW '24: Proceedings of the ACM Web Conference 2024Pages 4717–4726https://doi.org/10.1145/3589334.3648158Recommendation systems for Web content distribution intricately connect to the information access and exposure opportunities for vulnerable populations. The emergence of Large Language Models-based Recommendation System (LRS) may introduce additional ...
- research-articleMay 2024
Improving Item-side Fairness of Multimodal Recommendation via Modality Debiasing
WWW '24: Proceedings of the ACM Web Conference 2024Pages 4697–4705https://doi.org/10.1145/3589334.3648156Multimodal recommender systems have acquired applications in broad web scenarios such as e-commerce businesses and short-video platforms. Existing multimodal recommendation methods generally boost performance by introducing item-side multimodal content ...
- research-articleMay 2024
Towards Personalized Privacy: User-Governed Data Contribution for Federated Recommendation
WWW '24: Proceedings of the ACM Web Conference 2024Pages 3910–3918https://doi.org/10.1145/3589334.3645690Federated recommender systems (FedRecs) have gained significant attention for their potential to protect user's privacy by keeping user privacy data locally and only communicating model parameters/gradients to the server. Nevertheless, the currently ...
- research-articleMay 2024
Negative Sampling in Next-POI Recommendations: Observation, Approach, and Evaluation
WWW '24: Proceedings of the ACM Web Conference 2024Pages 3888–3899https://doi.org/10.1145/3589334.3645681To recommend the points of interest (POIs) that a user would check-in next, most deep-learning (DL)-based existing studies have employed random negative (RN) sampling during model training. In this paper, we claim and validate that, as the training ...
Benchmark and Neural Architecture for Conversational Entity Retrieval from a Knowledge Graph
WWW '24: Proceedings of the ACM Web Conference 2024Pages 1519–1528https://doi.org/10.1145/3589334.3645676This paper introduces a novel information retrieval (IR) task of Conversational Entity Retrieval from a Knowledge Graph (CER-KG), which extends non-conversational entity retrieval from a knowledge graph (KG) to the conversational scenario. The user ...
-
- research-articleMay 2024
General Debiasing for Graph-based Collaborative Filtering via Adversarial Graph Dropout
WWW '24: Proceedings of the ACM Web Conference 2024Pages 3864–3875https://doi.org/10.1145/3589334.3645667Graph neural networks (GNNs) have shown impressive performance in recommender systems, particularly in collaborative filtering (CF). The key lies in aggregating neighborhood information on a user-item interaction graph to enhance user/item ...
Perceptions in Pixels: Analyzing Perceived Gender and Skin Tone in Real-world Image Search Results
WWW '24: Proceedings of the ACM Web Conference 2024Pages 1249–1259https://doi.org/10.1145/3589334.3645666The results returned by image search engines have the power to shape peoples' perceptions about social groups. Existing work on image search engines leverages hand-selected queries for occupations like "doctor" and "engineer" to quantify racial and ...
- research-articleMay 2024
Can One Embedding Fit All? A Multi-Interest Learning Paradigm Towards Improving User Interest Diversity Fairness
WWW '24: Proceedings of the ACM Web Conference 2024Pages 1237–1248https://doi.org/10.1145/3589334.3645662Recommender systems (RSs) have gained widespread applications across various domains owing to the superior ability to capture users' interests. However, the complexity and nuanced nature of users' interests, which span a wide range of diversity, pose a ...
- research-articleMay 2024
M-scan: A Multi-Scenario Causal-driven Adaptive Network for Recommendation
WWW '24: Proceedings of the ACM Web Conference 2024Pages 3844–3853https://doi.org/10.1145/3589334.3645635We primarily focus on the field of multi-scenario recommendation, which poses a significant challenge in effectively leveraging data from different scenarios to enhance predictions in scenarios with limited data. Current mainstream efforts mainly center ...
- research-articleMay 2024
PMG : Personalized Multimodal Generation with Large Language Models
WWW '24: Proceedings of the ACM Web Conference 2024Pages 3833–3843https://doi.org/10.1145/3589334.3645633The emergence of large language models (LLMs) has revolutionized the capabilities of text comprehension and generation. Multi-modal generation attracts great attention from both the industry and academia, but there is little work on personalized ...
- research-articleMay 2024
Co-clustering for Federated Recommender System
WWW '24: Proceedings of the ACM Web Conference 2024Pages 3821–3832https://doi.org/10.1145/3589334.3645626As data privacy and security attract increasing attention, Federated Recommender System (FRS) offers a solution that strikes a balance between providing high-quality recommendations and preserving user privacy. However, the presence of statistical ...
- research-articleMay 2024
Reconciling the Accuracy-Diversity Trade-off in Recommendations
WWW '24: Proceedings of the ACM Web Conference 2024Pages 1318–1329https://doi.org/10.1145/3589334.3645625When making recommendations, there is an apparent trade-off between the goals of accuracy (to recommend items a user is most likely to want) and diversity (to recommend items representing a range of categories). As such, real-world recommender systems ...
- research-articleMay 2024
High-Frequency-aware Hierarchical Contrastive Selective Coding for Representation Learning on Text Attributed Graphs
WWW '24: Proceedings of the ACM Web Conference 2024Pages 4316–4327https://doi.org/10.1145/3589334.3645614We investigate node representation learning on text-attributed graphs (TAGs), where nodes are associated with text information. Although recent studies on graph neural networks (GNNs) and pretrained language models (PLMs) have exhibited their power in ...
- research-articleMay 2024
Fairness Rising from the Ranks: HITS and PageRank on Homophilic Networks
WWW '24: Proceedings of the ACM Web Conference 2024Pages 2594–2602https://doi.org/10.1145/3589334.3645609In this paper, we investigate the conditions under which link analysis algorithms prevent minority groups from reaching high ranking slots. We find that the most common link-based algorithms using centrality metrics, such as PageRank and HITS, can ...
Multimodal Relation Extraction via a Mixture of Hierarchical Visual Context Learners
WWW '24: Proceedings of the ACM Web Conference 2024Pages 4283–4294https://doi.org/10.1145/3589334.3645603Multimodal relation extraction is a fundamental task of multimodal information extraction. Recent studies have shown promising results by integrating hierarchical visual features from local regions, like image patches, to the broader global regions that ...
- research-articleMay 2024
RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules
WWW '24: Proceedings of the ACM Web Conference 2024Pages 4272–4282https://doi.org/10.1145/3589334.3645602Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open Web environment, since it requires ...
- research-articleMay 2024
Distributionally Robust Graph-based Recommendation System
WWW '24: Proceedings of the ACM Web Conference 2024Pages 3777–3788https://doi.org/10.1145/3589334.3645598With the capacity to capture high-order collaborative signals, Graph Neural Networks (GNNs) have emerged as powerful methods in Recommender Systems (RS). However, their efficacy often hinges on the assumption that training and testing data share the same ...
Author Name Disambiguation via Paper Association Refinement and Compositional Contrastive Embedding
WWW '24: Proceedings of the ACM Web Conference 2024Pages 2193–2203https://doi.org/10.1145/3589334.3645596Author name disambiguation (AND) is an essential task for online academic retrieval systems. Recent models adopt representation learning in the author's name disambiguation. Despite achieving remarkable success, these methods may be limited in two ...
- research-articleMay 2024
Enhancing Recommendation Accuracy and Diversity with Box Embedding: A Universal Framework
WWW '24: Proceedings of the ACM Web Conference 2024Pages 3756–3766https://doi.org/10.1145/3589334.3645577Recommender systems have emerged as an indispensable mean to meet personalized interests of users and alleviate information overload. Despite the great success, accuracy-oriented recommendation models are creating information cocoons, i.e., it is ...
- research-articleMay 2024
Unleashing the Power of Knowledge Graph for Recommendation via Invariant Learning
WWW '24: Proceedings of the ACM Web Conference 2024Pages 3745–3755https://doi.org/10.1145/3589334.3645576Knowledge graph (KG) demonstrates substantial potential for enhancing the performance of recommender systems. Due to its rich semantic content and associations among interactive entities, it can effectively alleviate inherent limitations in collaborative ...