paper-with-me

Papers

Enhancing Attributed Graph Networks with Alignment and Uniformity Constraints for Session-based Recommendation

2024-10-14 · Xinping Zhao, Chaochao Chen, Jiajie Su, Yizhao Zhang, Baotian Hu

Session-based Recommendation (SBR), seeking to predict a user's next action based on an anonymous session, has drawn increasing attention for its practicability. Most SBR models only rely on the contextual transitions within a short session to learn item representations while neglecting additional valuable knowledge. As such, their model capacity is largely limited by the data sparsity issue caused by short sessions. A few studies have exploited the Modeling of Item Attributes (MIA) to enrich item representations. However, they usually involve specific model designs that can hardly transfer to existing attribute-agnostic SBR models and thus lack universality. In this paper, we propose a model-agnostic framework, named AttrGAU (Attributed Graph Networks with Alignment and Uniformity Constraints), to bring the MIA's superiority into existing attribute-agnostic models, to improve their accuracy and robustness for recommendation. Specifically, we first build a bipartite attributed graph and design an attribute-aware graph convolution to exploit the rich attribute semantics hidden in the heterogeneous item-attribute relationship. We then decouple existing attribute-agnostic SBR models into the graph neural network and attention readout sub-modules to satisfy the non-intrusive requirement. Lastly, we design two representation constraints, i.e., alignment and uniformity, to optimize distribution discrepancy in representation between the attribute semantics and collaborative semantics. Extensive experiments on three public benchmark datasets demonstrate that the proposed AttrGAU framework can significantly enhance backbone models' recommendation performance and robustness against data sparsity and data noise issues. Our implementation codes will be available at https://github.com/ItsukiFujii/AttrGAU.

📄 PDF Abstract BibTeX arXiv:2410.10296

Code (1)

itsukifujii/attrgau 공식 구현

Tasks

AttributeGraph Neural NetworkSession-Based Recommendations

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

Generalizable Person Re-identification via Balancing Alignment and Uniformity

2024-11-18 · Yoonki Cho, Jaeyoon Kim, Woo Jae Kim, Junsik Jung 외

Domain generalizable person re-identification (DG re-ID) aims to learn discriminative representations that are robust to distributional shifts. While data augmentation is a straightforward solution to improve generalizat…

Data AugmentationGeneralizable Person Re-identificationPerson Re-Identification

Rethinking Graph Masked Autoencoders through Alignment and Uniformity

2024-02-11 · Xiang Tao, Qiang Liu, Shu Wu, Liang Wang

Self-supervised learning on graphs can be bifurcated into contrastive and generative methods. Contrastive methods, also known as graph contrastive learning (GCL), have dominated graph self-supervised learning in the past…

Contrastive LearningSelf-Supervised Learning

Graph-based Alignment and Uniformity for Recommendation

2023-08-18 · Liangwei Yang, Zhiwei Liu, Chen Wang, Mingdai Yang 외

Collaborative filtering-based recommender systems (RecSys) rely on learning representations for users and items to predict preferences accurately. Representation learning on the hypersphere is a promising approach due to…

Collaborative FilteringRecommendation SystemsRepresentation Learning

GCL-OT: Graph Contrastive Learning with Optimal Transport for Heterophilic Text-Attributed Graphs

2025-11-20 · Yating Ren, Yikun Ban, Huobin Tan arxiv

Recently, structure-text contrastive learning has shown promising performance on text-attributed graphs by leveraging the complementary strengths of graph neural networks and language models. However, existing methods ty…

Contrastive Learning

ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs

2026-06-09 · Xianlin Zeng, Fan Xia, Xiangyu Chen arxiv

Text-attributed Graphs (TAGs) incorporate textual node attributes with graph structures to describe rich relational semantics. Recent efforts to integrate Graph Neural Networks (GNNs) and Large Language Models (LLMs) hav…