With the booming of the Internet of Things (IoT) and the speedy advancement of Location-Based Social Networks (LBSNs), Point-Of-Interest (POI) recommendation has become a vital strategy for supporting people's ability to mine their POIs. However, classical recommendation models, such as collaborative filtering, are not effective for structuring POI recommendations due to the sparseness of user check-ins. Furthermore, LBSN recommendations are distinct from other recommendation scenarios. With respect to user data, a user's check-in record sequence requires rich social and geographic information. In this paper, we propose two different neural-network models, structural deep network Graph embedding Neural-network Recommendation system (SG-NeuRec) and Deepwalk on Graph Neural-network Recommendation system (DG-NeuRec) to improve POI recommendation. combined with embedding representation from social and geographical graph information (called SG-NeuRec and DG-NeuRec).Our model naturally combines the embedding representations of social and geographical graph information with user-POI interaction representation and captures the potential user-POI interactions under the framework of the neural network. Finally, we compare the performances of these two models and analyze the reasons for their differences. Results from comprehensive experiments on two real LBSNs datasets indicate the effective performance of our model.

Friend and point-of-interest (POI) recommendation are two primary individual services in location-based social networks (LBSNs). Major social platforms such as Foursquare and Instagram are all capable of recommending friends or POIs to individuals. However, most of these social websites make recommendations only based on similarity, popularity, or geographical influence; social trust among individuals has not been considered in those recommendation system. Recently, trust relationship has been proved to be helpful in collaborative recommendation. In this paper, we first propose algorithm to identify trust clusters and then give a trust prediction method based on these trust clusters. Then we combine the trust value and similarity among individuals to recommend friends to the target user. As for the POI recommendation, we devise a hybrid framework that integrates user preference, geographical influence, and trust relationship to improve the recommendation quality. In order to validate the effectiveness and efficiency of our methods, a series of experiments on two real social networks Foursquare and Instagram are conducted. The experiment results show that the trust cluster-based recommendation approach outperforms the baseline recommendation approaches in precision and recall.

The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality. The adversarial neural transfer (ANT) framework utilizes multiple loss terms that encourage the source-domain and the target-domain feature distributions to be similar while optimizing for domain-specific performance. However, these objectives may be in conflict, which can lead to optimization difficulties and sometimes diminished transfer. We propose a generalized latent optimization strategy that allows different losses to accommodate each other and improves training dynamics. The proposed method outperforms transfer learning and meta-learning baselines. In particular, we achieve 10.02% absolute performance gain over the previous state of the art on the iSarcasm dataset.

No abstract

Computational understanding of humor is an important topic under creative language understanding and modeling. It can play a key role in complex human-AI interactions. The challenge here is that human perception of humorous content is highly subjective. The same joke may receive different funniness ratings from different readers. This makes it highly challenging for humor recognition models to achieve personalization in practical scenarios. Existing approaches are generally designed based on the assumption that users have a consensus on whether a given text is humorous or not. Thus, they cannot handle diverse humor preferences well. In this article, we propose the FedHumor approach for the recognition of humorous content in a personalized manner through Federated Learning (FL). Extending a pre-trained language model, FedHumor guides the fine-tuning process by considering diverse distributions of humor preferences from individuals. It incorporates a diversity adaptation strategy into the FL paradigm to train a personalized humor recognition model. To the best of our knowledge, FedHumor is the first text-based personalized humor recognition model through federated learning. Extensive experiments demonstrate the advantage of FedHumor in recognizing humorous texts compared to nine state-of-the-art humor recognition approaches with superior capability for handling the diversity in humor labels produced by users with diverse preferences.