《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (6): 1869-1878.DOI: 10.11772/j.issn.1001-9081.2024060859
• 数据科学与技术 • 上一篇
颜文婧1,2, 王瑞东1,2, 左敏1,3(), 张青川1,2
收稿日期:
2024-06-25
修回日期:
2024-09-05
接受日期:
2024-09-06
发布日期:
2024-10-08
出版日期:
2025-06-10
通讯作者:
左敏
作者简介:
颜文婧(1985—),女,安徽淮南人,讲师,博士,主要研究方向:生物信息智能处理、深度学习基金资助:
Wenjing YAN1,2, Ruidong WANG1,2, Min ZUO1,3(), Qingchuan ZHANG1,2
Received:
2024-06-25
Revised:
2024-09-05
Accepted:
2024-09-06
Online:
2024-10-08
Published:
2025-06-10
Contact:
Min ZUO
About author:
YAN Wenjing, born in 1985, Ph. D., lecturer. Her research interests include intelligent processing of biological information, deep learning.Supported by:
摘要:
针对食谱推荐任务中信息维度不全面、交互数据稀疏和交互信息冗余的问题,提出一种基于风味嵌入异构图层次学习的食谱推荐模型(RecipeFlavor)。首先,引入风味分子维度,并基于用户、食物、食材和食材的风味物质构建异构图,有效表示4种节点之间的联系;其次,基于信息传递机制构建基于异构图的层级学习模块,并结合压缩注意力(SA)机制,将节点的不同关系视为不同的信息通道,提取节点之间的关键交互信息并抑制噪声;最后,基于特征感知噪声构建对比学习(CL)模块,在模型学习中引入正负样本区分任务,增强用户和食谱节点之间的信息关联,提升模型对特征的学习能力。实验结果表明,RecipeFlavor在Recipe 1M+大型数据集上,与HGAT(Hierarchical Graph ATtention network for recipe recommendation)模型相比,曲线下面积(AUC)提升了1.44个百分点,Top-10的模型精确度(Pre)、命中率(HR)、平均精度(MAP)和归一化折损累计增益(NDCG)分别提升了0.76、6.11、2.68和3.05个百分点。可见,风味分子信息的引入拓展了食谱推荐的学习维度,而RecipeFlavor能有效提取异构图中的关键信息,增强用户和食谱之间的关联性,从而提升食谱推荐的精度。
中图分类号:
颜文婧, 王瑞东, 左敏, 张青川. 基于风味嵌入异构图层次学习的食谱推荐模型[J]. 计算机应用, 2025, 45(6): 1869-1878.
Wenjing YAN, Ruidong WANG, Min ZUO, Qingchuan ZHANG. Recipe recommendation model based on hierarchical learning of flavor embedding heterogeneous graph[J]. Journal of Computer Applications, 2025, 45(6): 1869-1878.
节点类型 | 节点数 | 节点特征维度 |
---|---|---|
用户 | 7 959 | 300 |
食谱 | 68 794 | 1 024 |
食材 | 8 847 | 46 |
风味分子 | 1 524 | 256 |
表1 异构图的节点信息
Tab.1 Information of heterogeneous graph nodes
节点类型 | 节点数 | 节点特征维度 |
---|---|---|
用户 | 7 959 | 300 |
食谱 | 68 794 | 1 024 |
食材 | 8 847 | 46 |
风味分子 | 1 524 | 256 |
边的类型 | 边数 | 边的类型 | 边数 |
---|---|---|---|
用户-食谱 | 135 353 | 食谱-食谱 | 647 146 |
食谱-食材 | 463 485 | 食材-食材 | 146 188 |
食材-风味分子 | 588 255 | 用户-风味分子 | 1 755 267 |
表2 异构图的边信息
Tab.2 Information on heterogeneous graph edges
边的类型 | 边数 | 边的类型 | 边数 |
---|---|---|---|
用户-食谱 | 135 353 | 食谱-食谱 | 647 146 |
食谱-食材 | 463 485 | 食材-食材 | 146 188 |
食材-风味分子 | 588 255 | 用户-风味分子 | 1 755 267 |
K | Pre | HR | MAP | NDCG |
---|---|---|---|---|
2 | 10.94 | 23.82 | 20.82 | 23.82 |
4 | 7.44 | 31.01 | 23.30 | 29.06 |
6 | 6.04 | 37.75 | 24.94 | 32.78 |
8 | 5.27 | 43.50 | 26.19 | 35.85 |
10 | 4.88 | 48.75 | 27.21 | 38.48 |
表3 RecipeFlavor的Top-K配方推荐的性能 (%)
Tab.3 Top-K formulation recommendation performance of RecipeFlavor
K | Pre | HR | MAP | NDCG |
---|---|---|---|---|
2 | 10.94 | 23.82 | 20.82 | 23.82 |
4 | 7.44 | 31.01 | 23.30 | 29.06 |
6 | 6.04 | 37.75 | 24.94 | 32.78 |
8 | 5.27 | 43.50 | 26.19 | 35.85 |
10 | 4.88 | 48.75 | 27.21 | 38.48 |
模型 | 食谱图像信息 | 食材 信息 | 营养 信息 | 风味分子信息 | 关系 种类数 |
---|---|---|---|---|---|
MF-BPR | × | × | × | × | 1 |
NGCF | × | × | × | × | 1 |
HAFR | √ | √ | × | × | 1 |
CMV-SHGNFR | √ | √ | √ | × | 2 |
SCHGN | √ | √ | √ | × | 3 |
HGAT | √ | √ | √ | × | 4 |
RecipeFlavor | √ | √ | √ | √ | 6 |
表4 模型构建使用信息的总结
Tab. 4 Summary of information used in model construction
模型 | 食谱图像信息 | 食材 信息 | 营养 信息 | 风味分子信息 | 关系 种类数 |
---|---|---|---|---|---|
MF-BPR | × | × | × | × | 1 |
NGCF | × | × | × | × | 1 |
HAFR | √ | √ | × | × | 1 |
CMV-SHGNFR | √ | √ | √ | × | 2 |
SCHGN | √ | √ | √ | × | 3 |
HGAT | √ | √ | √ | × | 4 |
RecipeFlavor | √ | √ | √ | √ | 6 |
模型 | AUC | HR | NDCG | Pre | MAP |
---|---|---|---|---|---|
MF-BPR | 56.22 | 7.30 | 15.68 | 1.25 | 4.99 |
NGCF | 58.28 | 5.20 | 10.68 | 3.24 | 19.48 |
HAFR | 64.35 | 8.84 | 18.64 | ||
CMV-SHGNFR | 68.44 | 9.55 | 20.83 | ||
SCHGN | 72.12 | 11.05 | 24.43 | ||
HGAT | 74.36 | 32.37 | 45.70 | 4.12 | 24.53 |
RecipeFlavor | 75.80 | 38.48 | 48.75 | 4.88 | 27.21 |
表5 不同模型在Top-10的实验结果 (单位%)
Tab.5 Top-10 experimental results of different models
模型 | AUC | HR | NDCG | Pre | MAP |
---|---|---|---|---|---|
MF-BPR | 56.22 | 7.30 | 15.68 | 1.25 | 4.99 |
NGCF | 58.28 | 5.20 | 10.68 | 3.24 | 19.48 |
HAFR | 64.35 | 8.84 | 18.64 | ||
CMV-SHGNFR | 68.44 | 9.55 | 20.83 | ||
SCHGN | 72.12 | 11.05 | 24.43 | ||
HGAT | 74.36 | 32.37 | 45.70 | 4.12 | 24.53 |
RecipeFlavor | 75.80 | 38.48 | 48.75 | 4.88 | 27.21 |
模型 | Pre | HR | MAP | NDCG |
---|---|---|---|---|
FRec_base | 4.58 | 45.84 | 25.47 | 35.65 |
FRec_SA | 4.65 | 46.52 | 26.48 | 36.49 |
FRec_NCL | 4.68 | 46.62 | 25.84 | 37.47 |
RecipeFlavor | 4.88 | 48.75 | 27.21 | 38.48 |
表6 在Top-10的消融实验结果 (单位%)
Tab.6 Top-10 ablation experimental results
模型 | Pre | HR | MAP | NDCG |
---|---|---|---|---|
FRec_base | 4.58 | 45.84 | 25.47 | 35.65 |
FRec_SA | 4.65 | 46.52 | 26.48 | 36.49 |
FRec_NCL | 4.68 | 46.62 | 25.84 | 37.47 |
RecipeFlavor | 4.88 | 48.75 | 27.21 | 38.48 |
K=1 | K=5 | K=10 | ||||
---|---|---|---|---|---|---|
HR/% | NDCG/% | HR/% | NDCG/% | HR/% | NDCG/% | |
0.1 | 17.90 | 17.90 | 31.75 | 28.55 | 44.74 | 35.11 |
0.2 | 18.13 | 18.13 | 33.52 | 30.33 | 46.88 | 37.05 |
0.3 | 18.04 | 18.04 | 32.85 | 29.68 | 44.92 | 35.98 |
0.4 | 18.10 | 18.10 | 33.44 | 29.85 | 45.96 | 36.29 |
0.5 | 18.19 | 18.19 | 32.99 | 29.67 | 46.35 | 36.23 |
表7 不同损失权重系数λ下模型的性能
Tab.7 Model performance under different loss weight coefficient λ
K=1 | K=5 | K=10 | ||||
---|---|---|---|---|---|---|
HR/% | NDCG/% | HR/% | NDCG/% | HR/% | NDCG/% | |
0.1 | 17.90 | 17.90 | 31.75 | 28.55 | 44.74 | 35.11 |
0.2 | 18.13 | 18.13 | 33.52 | 30.33 | 46.88 | 37.05 |
0.3 | 18.04 | 18.04 | 32.85 | 29.68 | 44.92 | 35.98 |
0.4 | 18.10 | 18.10 | 33.44 | 29.85 | 45.96 | 36.29 |
0.5 | 18.19 | 18.19 | 32.99 | 29.67 | 46.35 | 36.23 |
K=1 | K=5 | K=10 | ||||
---|---|---|---|---|---|---|
HR/% | NDCG/% | HR/% | NDCG/% | HR/% | NDCG/% | |
0.1 | 18.03 | 18.03 | 32.37 | 29.12 | 45.15 | 35.54 |
0.2 | 18.07 | 18.07 | 34.01 | 30.61 | 46.57 | 37.03 |
0.3 | 18.00 | 18.00 | 33.30 | 30.04 | 46.39 | 36.67 |
0.4 | 18.32 | 18.32 | 33.43 | 30.03 | 46.48 | 36.54 |
0.5 | 17.79 | 17.79 | 32.71 | 29.41 | 45.08 | 35.86 |
表8 不同噪声约束υ下模型的性能
Tab.8 Model performance under different noise constraint υ
K=1 | K=5 | K=10 | ||||
---|---|---|---|---|---|---|
HR/% | NDCG/% | HR/% | NDCG/% | HR/% | NDCG/% | |
0.1 | 18.03 | 18.03 | 32.37 | 29.12 | 45.15 | 35.54 |
0.2 | 18.07 | 18.07 | 34.01 | 30.61 | 46.57 | 37.03 |
0.3 | 18.00 | 18.00 | 33.30 | 30.04 | 46.39 | 36.67 |
0.4 | 18.32 | 18.32 | 33.43 | 30.03 | 46.48 | 36.54 |
0.5 | 17.79 | 17.79 | 32.71 | 29.41 | 45.08 | 35.86 |
K=1 | K=5 | K=10 | ||||
---|---|---|---|---|---|---|
HR/% | NDCG/% | HR/% | NDCG/% | HR/% | NDCG/% | |
0.05 | 18.19 | 18.19 | 33.52 | 30.09 | 47.61 | 37.53 |
0.07 | 18.56 | 18.56 | 34.38 | 30.66 | 48.61 | 38.17 |
0.09 | 18.38 | 18.38 | 34.54 | 31.07 | 48.75 | 38.48 |
0.11 | 17.81 | 17.81 | 33.46 | 29.77 | 48.00 | 37.25 |
0.13 | 18.17 | 18.17 | 33.85 | 30.23 | 48.22 | 37.79 |
0.15 | 17.66 | 17.66 | 34.66 | 30.83 | 48.55 | 38.19 |
表9 不同温度系数τ下模型的性能
Tab.9 Model performance under different temperature coefficient τ
K=1 | K=5 | K=10 | ||||
---|---|---|---|---|---|---|
HR/% | NDCG/% | HR/% | NDCG/% | HR/% | NDCG/% | |
0.05 | 18.19 | 18.19 | 33.52 | 30.09 | 47.61 | 37.53 |
0.07 | 18.56 | 18.56 | 34.38 | 30.66 | 48.61 | 38.17 |
0.09 | 18.38 | 18.38 | 34.54 | 31.07 | 48.75 | 38.48 |
0.11 | 17.81 | 17.81 | 33.46 | 29.77 | 48.00 | 37.25 |
0.13 | 18.17 | 18.17 | 33.85 | 30.23 | 48.22 | 37.79 |
0.15 | 17.66 | 17.66 | 34.66 | 30.83 | 48.55 | 38.19 |
1 | XIE W, LOU H. Implementation of key technologies for a healthy food culture recommendation system using internet of things[J]. Mobile Information Systems, 2022, 2022: No.9675452. |
2 | MAJJODI A EL, STARKE A D, TRATTNER C. Nudging towards health? examining the merits of nutrition labels and personalization in a recipe recommender system [C]// Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization. New York: ACM, 2022: 48-56. |
3 | ELSWEILER D, TRATTNER C, HARVEY M. Exploiting food choice biases for healthier recipe recommendation [C]// Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2017: 575-584. |
4 | WU S, SUN F, ZHANG W, et al. Graph neural networks in recommender systems: a survey[J]. ACM Computing Surveys, 2023, 55(5): No.97. |
5 | GAO Y, HUANG Z W, HUANG Z Y, et al. Multi-scale broad collaborative filtering for personalized recommendation[J]. Knowledge-Based Systems, 2023, 278: No.110853. |
6 | ZHANG S, YAO L, SUN A, et al. Deep learning based recommender system: a survey and new perspectives[J]. ACM Computing Surveys, 2020, 52(1): No.5. |
7 | MIN W, JIANG S, JAIN R. Food recommendation: framework, existing solutions, and challenges[J]. IEEE Transactions on Multimedia, 2020, 22(10): 2659-2671. |
8 | MAHAJAN P, KAUR P D. A systematic literature review of food recommender systems[J]. SN Computer Science, 2024, 5: No.174. |
9 | RHODES D G, MORTON S, MYROWITZ R, et al. Food and nutrient database for dietary studies 2019-2020: an application database for national dietary surveillance[J]. Journal of Food Composition and Analysis, 2023, 123: No.105547. |
10 | MARÍN J, BISWAS A, OFLI F, et al. Recipe1M+: a dataset for learning cross-modal embeddings for cooking recipes and food images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(1): 187-203. |
11 | GUO Q, ZHUANG F, QIN C, et al. A survey on knowledge graph-based recommender systems [J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(8): 3549-3568. |
12 | ZHANG S, LIN X, BAI Z, et al. CGRS: collaborative knowledge propagation graph attention network for recipes recommendation[J]. Connection Science, 2023, 35(1): No.2212883. |
13 | GAO X, FENG F, HUANG H, et al. Food recommendation with graph convolutional network[J]. Information Sciences, 2022, 584: 170-183. |
14 | MORALES-GARZÓN A, GUTIÉRREZ-BATISTA K, MARTIN-BAUTISTA M J. Link prediction in food heterogeneous graphs for personalised recipe recommendation based on user interactions and dietary restrictions [J]. Computing, 2024, 106(7): 2133-2155. |
15 | LI Y, ZHAO F, CHEN Z, et al. Multi-behavior enhanced heterogeneous graph convolutional networks recommendation algorithm based on feature-interaction[J]. Applied Artificial Intelligence, 2023, 37(1): No.2201144. |
16 | ZHU S, ZHOU C, PAN S, et al. Relation structure-aware heterogeneous graph neural network [C]// Proceedings of the 2019 IEEE International Conference on Data Mining. Piscataway: IEEE, 2019: 1534-1539. |
17 | BING R, YUAN G, ZHU M, et al. Heterogeneous graph neural networks analysis: a survey of techniques, evaluations and applications[J]. Artificial Intelligence Review, 2023, 56(8): 8003-8042. |
18 | TIAN Y, ZHANG C, METOYER R, et al. Recipe recommendation with hierarchical graph attention network[J]. Frontiers in Big Data, 2021, 4: No.778417. |
19 | TIAN Y, ZHANG C, GUO Z, et al. RecipeRec: a heterogeneous graph learning model for recipe recommendation [C]// Proceedings of the 31st International Joint Conference on Artificial Intelligence. California: ijcai.org, 2022: 3466-3472. |
20 | SONG Y, YANG X, XU C. Self-supervised calorie-aware heterogeneous graph networks for food recommendation[J]. ACM Transactions on Multimedia Computing Communications and Applications, 2023, 19(1s): No.27. |
21 | BONDEVIK J N, BENNIN K E, BABUR Ö, et al. A systematic review on food recommender systems[J]. Expert System with Applications, 2024, 238(Pt E): No.122166. |
22 | AHN Y Y, AHNERT S E, BAGROW J P, et al. Flavor network and the principles of food pairing[J]. Scientific Reports, 2011, 1: No.196. |
23 | 左敏,王菲,宋绍义,等. “智慧+食品监管”:发展历程、应用现状与未来方向[J]. 食品科学技术学报, 2024, 42(3): 1-10. |
ZUO M, WANG F, SONG S Y, et al. “Intelligence+food regulation”: development process, current application status, and future direction[J]. Journal of Food Science and Technology, 2024, 42(3):1-10. | |
24 | 厦门大学. 一种能够提高便利性的食谱推荐系统: 202310497806.5 [P]. 2023-08-01. |
Xiamen University. A recipe recommendation system that can improve convenience: 202310497806.5 [P]. 2023-08-01. | |
25 | JIANG X, LU Y, FANG Y, et al. Contrastive pre-training of GNNs on heterogeneous graphs [C]// Proceedings of the 30th ACM International Conference on Information and Knowledge Management. New York: ACM, 2021: 803-812. |
26 | LEI Z, UL HAQ A, ZEB A, et al. Is the suggested food your desired?: Multi-modal recipe recommendation with demand-based knowledge graph[J]. Expert Systems with Applications, 2021, 186: No.115708. |
27 | 宋亚光,杨小汕,徐常胜. 跨模态多视角自监督的个性化食谱推荐异构图网络 [J]. 计算机辅助设计与图形学学报, 2023, 35(3): 413-422. |
SONG Y G, YANG X S, XU C S. A cross-modal multi-view self-supervised heterogeneous graph network for personalized food recommendation [J]. Journal of Computer-Aided Design and Computer Graphics, 2023, 35(3): 413-422. | |
28 | FOROUZANDEH S, ROSTAMI M, BERAHMAND K, et al. Health-aware food recommendation system with dual attention in heterogeneous graphs[J]. Computers in Biology and Medicine, 2024, 169: No.107882. |
29 | GAO T, YAO X, CHEN D. SimCSE: simple contrastive learning of sentence embeddings [C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2021: 6894-6910. |
30 | HE K, FAN H, WU Y, et al. Momentum contrast for unsupervised visual representation learning[C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 9726-9735. |
31 | 雷景生,剌凯俊,杨胜英,等. 基于上下文语义增强的实体关系联合抽取[J]. 计算机应用, 2023, 43(5): 1438-1444. |
LEI J S, LA K J, YANG S Y, et al. Joint entity and relation extraction based on contextual semantic enhancement[J]. Journal of Computer Applications, 2023, 43(5): 1438-1444. | |
32 | YU J L, YIN H Z, GAO M, et al. Socially-aware self-supervised tri-training for recommendation [C]// Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2021: 2084-2092. |
33 | CHEN M, HUANG C, XIA L, et al. Heterogeneous graph contrastive learning for recommendation [C]// Proceedings of the 16th ACM International Conference on Web Search and Data Mining. New York: ACM, 2023: 544-552. |
34 | GARG N, SETHUPATHY A, TUWANI R, et al. FlavorDB: a database of flavor molecules [J]. Nucleic Acids Research, 2018, 46(D1): D1210-D1216. |
35 | 左敏,胡静珺,颜文婧,等. 基于嗅觉受体激活关系模拟的气味感知预测[J]. 中山大学学报(自然科学版(中英文)), 2024, 63(1): 86-95. |
ZUO M, HU J J, YAN W J, et al. Prediction of olfactory perception based on simulation of olfactory receptor activation relationships[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2024, 63(1):86-95. | |
36 | HAUSSMANN S, SENEVIRATNE O, CHEN Y, et al. FoodKG: a semantics-driven knowledge graph for food recommendation [C]// Proceedings of the 2019 International Semantic Web Conference, LNCS 11779. Cham: Springer, 2019: 146-162. |
37 | TIAN Y, ZHANG C, METOYER R, et al. Recipe representation learning with networks[C]// Proceedings of the 30th ACM International Conference on Information and Knowledge Management. New York: ACM, 2021: 1824-1833. |
38 | VAN DEN OORD A, LI Y, VINYALS O. Representation learning with contrastive predictive coding[EB/OL]. [2024-08-29].. |
39 | BATRA D, DIWAN N, UPADHYAY U, et al. RecipeDB: a resource for exploring recipes[J]. Database, 2020, 2020: No.baaa077. |
40 | HE X, LIAO L, ZHANG H, et al. Neural collaborative filtering[C]// Proceedings of the 26th International Conference on World Wide Web. Republic and Canton of Geneva: International World Wide Web Conferences Steering Committee, 2017: 173-182. |
41 | RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR: Bayesian personalized ranking from implicit feedback[C]// Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. Arlington, VA: AUAI Press, 2009: 452-461. |
42 | WANG X, HE X, WANG M, et al. Neural graph collaborative filtering[C]// Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2019: 165-174. |
43 | GAO X, FENG F, HE X, et al. Hierarchical attention network for visually-aware food recommendation[J]. IEEE Transactions on Multimedia, 2020, 22(6): 1647-1659. |
44 | ABDI H, WILLIAMS L J. Principal component analysis[J]. WIREs Computational Statistics, 2010, 2(4): 433-459. |
[1] | 姜超英, 李倩, 刘宁, 刘磊, 崔立真. 基于图对比学习的再入院预测模型[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1784-1792. |
[2] | 余明峰, 秦永彬, 黄瑞章, 陈艳平, 林川. 基于对比学习增强双注意力机制的多标签文本分类方法[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1732-1740. |
[3] | 吴宗航, 张东, 李冠宇. 基于联合自监督学习的多模态融合推荐算法[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1858-1868. |
[4] | 李自亮, 朱广丽, 张玉雷, 刘佳佳, 焦熠璇, 张顺香. 集成句法与情感知识的方面级情感分析模型[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1724-1731. |
[5] | 王泉, 陆啟想, 施珮. 用于交通流量预测的多图扩散注意力网络[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1472-1479. |
[6] | 陈昕, 刘忠慧, 闵帆. 约简形式背景下的概念集构造及其推荐应用[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1415-1423. |
[7] | 胡文彬, 蔡天翔, 韩天乐, 仲兆满, 马常霞. 融合对比学习与情感分析的多模态反讽检测模型[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1432-1438. |
[8] | 龙雨菲, 牟宇辰, 刘晔. 基于张量化图卷积网络和对比学习的多源数据表示学习模型[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1372-1378. |
[9] | 陈满, 杨小军, 杨慧敏. 基于图卷积网络和终点诱导的行人轨迹预测[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1480-1487. |
[10] | 田仁杰, 景明利, 焦龙, 王飞. 基于混合负采样的图对比学习推荐算法[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1053-1060. |
[11] | 党伟超, 温鑫瑜, 高改梅, 刘春霞. 基于多视图多尺度对比学习的图协同过滤[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1061-1068. |
[12] | 党伟超, 宋楚君, 高改梅, 刘春霞. 基于级联残差图卷积网络的多行为推荐[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1223-1231. |
[13] | 陈维, 施昌勇, 马传香. 基于多模态数据融合的农作物病害识别方法[J]. 《计算机应用》唯一官方网站, 2025, 45(3): 840-848. |
[14] | 王元龙, 刘亭华, 张虎. 基于跨模态对比学习的常识问答模型[J]. 《计算机应用》唯一官方网站, 2025, 45(3): 732-738. |
[15] | 富坤, 应世聪, 郑婷婷, 屈佳捷, 崔静远, 李建伟. 面向小样本节点分类的图数据增强方法[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 392-402. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||