จำนวนผู้เข้าชม
24
Creative Commons License
| Collection | RMUTK Research Repository (RMUTK IR) วารสารวิชาการ — e-Journal Articles |
| ID RMUTK Digital | RMUTK000021 |
| Title | |
| Alternative title | GCTMR: Graph Contrastive Transformer for Multibehavior Recommendation |
| Authors | ผศ.ดร.นิกร กรรณิกากลาง ผู้แต่งหลัก |
| Faculty | คณะบริหารธุรกิจ |
| Journal Title | IEEE Access |
| ISSN | 2169-3536 |
| Volume / Issue / Pages | Vol.14 | No.- | pp.109651 - 109669 |
| Published | 2026-07-17 |
| Year | 2569 |
| Level | ระดับนานาชาติ (SCOPUS) |
| Quartile | Q1 |
| DOI | 10.1109/ACCESS.2026.3714484 |
| Abstract | Multibehavior recommendation aims to leverage diverse user interaction types—such as views, clicks, and purchases—to better understand user intent and enhance recommendation accuracy. However, effectively modeling these heterogeneous behaviors remains challenging due to the sparsity, noise, over-smooth embedding, and dynamic nature of interaction sequences. To address these issues, we propose GCTMR (Graph Contrastive Transformer for Multibehavior Recommendation), a framework that integrates graph-based contrastive learning with a behavior-aware Transformer architecture. Specifically, the methodological contribution lies in three key innovations: 1) an adaptive sparse attention mechanism employing α -entmax that dynamically filters out noisy or irrelevant interactions to preserve the distinctiveness of user behavior representations; 2) a frequency-aware multibehavior encoder using FFT/IFFT decomposition that disentangles stable long-term preferences from short-term behavioral shifts across different interaction types; and 3) a simplified focal loss function that emphasizes hard-to-predict instances, improving robustness under data sparsity and behavioral ambiguity. The empirical validation is exceptionally strong, demonstrating improving of 22.43% on Tmall and 18.10% on Beibei over state-of-the-art baselines in HR@10 metrics, with particularly remarkable performance under sparse data conditions where traditional methods struggle most. Comprehensive ablation studies confirm that each component contributes meaningfully to the overall performance, while extensive hyperparameter analyses demonstrate the framework’s stability and practical applicability. |
| Abstract (EN) | Multibehavior recommendation aims to leverage diverse user interaction types—such as views, clicks, and purchases—to better understand user intent and enhance recommendation accuracy. However, effectively modeling these heterogeneous behaviors remains challenging due to the sparsity, noise, over-smooth embedding, and dynamic nature of interaction sequences. To address these issues, we propose GCTMR (Graph Contrastive Transformer for Multibehavior Recommendation), a framework that integrates graph-based contrastive learning with a behavior-aware Transformer architecture. Specifically, the methodological contribution lies in three key innovations: 1) an adaptive sparse attention mechanism employing α -entmax that dynamically filters out noisy or irrelevant interactions to preserve the distinctiveness of user behavior representations; 2) a frequency-aware multibehavior encoder using FFT/IFFT decomposition that disentangles stable long-term preferences from short-term behavioral shifts across different interaction types; and 3) a simplified focal loss function that emphasizes hard-to-predict instances, improving robustness under data sparsity and behavioral ambiguity. The empirical validation is exceptionally strong, demonstrating improving of 22.43% on Tmall and 18.10% on Beibei over state-of-the-art baselines in HR@10 metrics, with particularly remarkable performance under sparse data conditions where traditional methods struggle most. Comprehensive ablation studies confirm that each component contributes meaningfully to the overall performance, while extensive hyperparameter analyses demonstrate the framework’s stability and practical applicability. |
| Keywords (TH) | Graph contrastive learningmultibehavior recommendationtransformer recommendation |
| Keywords (EN) | Graph contrastive learningmultibehavior recommendationtransformer recommendation |
| Access Level | Open Access (เปิดสาธารณะ) |
ลิงก์แหล่งเผยแพร่
เอกสารฉบับเต็ม (ลิงก์ภายนอก)
https://ieeexplore.ieee.org/document/11613967
รายการที่เกี่ยวข้อง
การศึกษาเปรียบเทียบสถาปัตยกรรม YOLO สำหรับการตรวจจับข้อบกพร่องบนรอยเชื
ผศ.สุรเทพ แป้นเกิด · 2569 · 255
การจําแนกข้อความ SMS ภาษาไทย จากมิจฉาชีพ ด้วย Machine Learning
ผศ.สุรเทพ แป้นเกิด · 2569 · 246
เครื่องต้นแบบพัฒนาภาษามือโดยใช้เทคโนโลยี IoT
ผศ.สุรเทพ แป้นเกิด · 2569 · 245
การวิเคราะห์ความเสี่ยงด้านการสื่อสารข้ามวัฒนธรรมที่มีอิทธิพลต่อประสิทธ
ผศ.ดร.ณัฐรฐนนท์ กานต์รวีกุลธนา · 2569 · 97