<p>Cross-domain sequential recommendation (CDSR) aims to predict future sequential interactions in a target domain by analyzing historical sequence data from different domains. A significant challenge in CDSR is the accurate capture of user preferences based on the target domain and multiple domains. Existing methodologies to enhance the performance of the target domain primarily focus on learning preferences for a single domain within each respective domain and subsequently transferring this knowledge to the target domain via a transferring module. However, this approach inadequately accounts for the linear relationship between the target domain and user preferences, thereby limiting the potential benefits of leveraging target domain knowledge to enhance performance in rich domains. This study introduces a novel Contrastive cross-domain sequential recommendation technique with an attention-aware mechanism (<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="40747_2025_1856_Article_IEq1.gif" Format="GIF" Height="17" Rendition="HTML" Resolution="72" Type="Linedraw" Width="71" /> </InlineMediaObject> <EquationSource Format="TEX">$\hbox {C}^2\hbox {DSRA}^2$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <msup> <mtext>C</mtext> <mn>2</mn> </msup> <msup> <mtext>DSRA</mtext> <mn>2</mn> </msup> </mrow> </math></EquationSource> </InlineEquation>) for CDSR. We use graph neural networks (GNNs) combined with attention-aware mechanisms to elucidate the relationship between cross-domain and target domain user preferences. Specifically, we first develop an attention-aware framework over GNNs to capture collaborative relationships among inter-sequence items, then propose an attenuation function to assess the rationality of item representations. We construct cross-domain representations using the attention-aware mechanism to derive user-specific target domain representations. <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="40747_2025_1856_Article_IEq1.gif" Format="GIF" Height="17" Rendition="HTML" Resolution="72" Type="Linedraw" Width="71" /> </InlineMediaObject> <EquationSource Format="TEX">$\hbox {C}^2\hbox {DSRA}^2$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <msup> <mtext>C</mtext> <mn>2</mn> </msup> <msup> <mtext>DSRA</mtext> <mn>2</mn> </msup> </mrow> </math></EquationSource> </InlineEquation> enhances recommendation performance and practical applicability. Experiments show <InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="40747_2025_1856_Article_IEq1.gif" Format="GIF" Height="17" Rendition="HTML" Resolution="72" Type="Linedraw" Width="71" /> </InlineMediaObject> <EquationSource Format="TEX">$\hbox {C}^2\hbox {DSRA}^2$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <msup> <mtext>C</mtext> <mn>2</mn> </msup> <msup> <mtext>DSRA</mtext> <mn>2</mn> </msup> </mrow> </math></EquationSource> </InlineEquation> surpasses state-of-the-art (SOTA) cross-domain recommendation algorithms.</p>

Contrastive cross-domain sequential recommendation with attention-aware mechanism

期刊论文
出版模式：

开放获取
发表日期：

2025年4月22日

查看全文

Wei Zhao,
Bo Li,
Xian Mo

摘要

Cross-domain sequential recommendation (CDSR) aims to predict future sequential interactions in a target domain by analyzing historical sequence data from different domains. A significant challenge in CDSR is the accurate capture of user preferences based on the target domain and multiple domains. Existing methodologies to enhance the performance of the target domain primarily focus on learning preferences for a single domain within each respective domain and subsequently transferring this knowledge to the target domain via a transferring module. However, this approach inadequately accounts for the linear relationship between the target domain and user preferences, thereby limiting the potential benefits of leveraging target domain knowledge to enhance performance in rich domains. This study introduces a novel Contrastive cross-domain sequential recommendation technique with an attention-aware mechanism ( $\hbox {C}^2\hbox {DSRA}^2$ $C^{2} {DSRA}^{2}$ ) for CDSR. We use graph neural networks (GNNs) combined with attention-aware mechanisms to elucidate the relationship between cross-domain and target domain user preferences. Specifically, we first develop an attention-aware framework over GNNs to capture collaborative relationships among inter-sequence items, then propose an attenuation function to assess the rationality of item representations. We construct cross-domain representations using the attention-aware mechanism to derive user-specific target domain representations. $\hbox {C}^2\hbox {DSRA}^2$ $C^{2} {DSRA}^{2}$ enhances recommendation performance and practical applicability. Experiments show $\hbox {C}^2\hbox {DSRA}^2$ $C^{2} {DSRA}^{2}$ surpasses state-of-the-art (SOTA) cross-domain recommendation algorithms.