Knowledge-aware Dual-side Attribute-enhanced Recommendation

$\mathit{\text{Knowledge-aware}}$ recommendation methods (KGR) based on $\mathit{\text{graph}}\mathit{\text{neural}}\mathit{\text{networks}}$ (GNNs) and $\mathit{\text{contrastive}}\mathit{\text{learning}}$ (CL) have achieved promising performance. However, they fall short in modeling fine-grained user preferences and further fail to leverage the $\mathit{\text{preference-attribute}}\mathit{\text{connection}}$ to make predictions, leading to sub-optimal performance. To address the issue, we propose a method named $\mathit{\text{K}}\mathit{\text{nowledge-aware}}\mathit{\text{D}}\mathit{\text{ual-side}}\mathit{\text{A}}\mathit{\text{ttribute-enhanced}}\mathit{\text{R}}\mathit{\text{ecommendation}}$ (KDAR). Specifically, we build $\mathit{\text{user}}\mathit{\text{preference}}\mathit{\text{representations}}$ and $\mathit{\text{attribute}}\mathit{\text{fusion}}\mathit{\text{representations}}$ upon the attribute information in knowledge graphs, which are utilized to enhance $\mathit{\text{collaborative}}\mathit{\text{filtering}}$ (CF) based user and item representations, respectively. To discriminate the contribution of each attribute in these two types of attribute-based representations, a $\mathit{\text{multi-level}}\mathit{\text{collaborative}}\mathit{\text{alignment}}\mathit{\text{contrasting}}$ mechanism is proposed to align the importance of attributes with CF signals. Experimental results on four benchmark datasets demonstrate the superiority of KDAR over several state-of-the-art baselines. Further analyses verify the effectiveness of our method. The code of KDAR is released at: \href{https://github.com/TJTP/KDAR}{https://github.com/TJTP/KDAR}.