CityTransfer: Transferring Inter- and Intra-City Knowledge for Chain Store Site Recommendation based on Multi-Source Urban Data
Chain businesses have been dominating the market in many parts of the world. It is important to identify the optimal locations for a new chain store. Recently, numerous studies have been done on chain store location recommendation. These studies typically learn a model based on the features of existing chain stores in the city and then predict what other sites are suitable for running a new one. However, these models do not work when a chain enterprise wants to open business in a new city where there is not enough data about this chain store. To solve the cold-start problem, we propose CityTransfer, which transfers chain store knowledge from semantically-relevant domains (e.g., other cities with rich knowledge, similar chain enterprises in the target city) for chain store placement recommendation in a new city. In particular, CityTransfer is a two-fold knowledge transfer framework based on collaborative filtering, which consists of the transfer rating prediction model, the inter-city knowledge association method and the intra-city semantic extraction method. Experiments using data of chain hotels from four different cities crawled from Ctrip (a popular travel reservation website in China) and the urban characters extracted from several other data sources validate the effectiveness of our approach on store site recommendation.
Code (1)
Tasks
Collaborative FilteringTransfer LearningSimilar Papers 제목 키워드 기반
I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation
This paper proposes a new knowledge distillation method tailored for image semantic segmentation, termed Intra- and Inter-Class Knowledge Distillation (I2CKD). The focus of this method is on capturing and transferring kn…
Knowledge DistillationSegmentationSemantic SegmentationTransfer Learning+1CityGen: Structure-Guided City-Style Synthesis for Cross-City Autonomous Driving
Autonomous driving systems are commonly trained and evaluated within limited geographic regions, which hinders their scalability when deployed in new cities. However, significant domain shifts in appearance, road topolog…
Synthetic Data GenerationAutonomous DrivingData AugmentationDomain AdaptationIntra-class Feature Variation Distillation for Semantic Segmentation
Current state-of-the-art semantic segmentation methods usually require high computational resources for accurate segmentation. One promising way to achieve a good trade-off between segmentation accuracy and efficiency is…
Knowledge DistillationSegmentationSemantic SegmentationCORSD: Class-Oriented Relational Self Distillation
Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature map but are lack of transferring the re…
Knowledge DistillationModel CompressionRelationRelation ExtractionGraph Relation Distillation for Efficient Biomedical Instance Segmentation
Instance-aware embeddings predicted by deep neural networks have revolutionized biomedical instance segmentation, but its resource requirements are substantial. Knowledge distillation offers a solution by transferring di…
Instance SegmentationKnowledge DistillationRelationSemantic Segmentation