The point-of-interest (POI) recommendation predicts users' destinations, which might be of interest to users and has attracted considerable attention as one of the major applications in location-based social networks (LBSNs). Recent work on graph-based neural networks (GNN) or matrix factorization-based (MF) approaches has resulted in better representations of users and POIs to forecast users' latent preferences. However, they still suffer from the implicit feedback and cold-start problems of check-in data, as they cannot capture both local and global graph-based relations among users (or POIs) simultaneously, and the cold-start neighbors are not handled properly during graph convolution in GNN. In this paper, we propose an enhanced encoder-decoder network (EEDN) to exploit rich latent features between users, POIs, and interactions between users and POIs for POI recommendation. The encoder of EEDN utilizes a hybrid hypergraph convolution to enhance the aggregation ability of each graph convolution step and learns to derive more robust cold-start-aware user representations. In contrast, the decoder mines local and global interactions by both graph- and sequential-based patterns for modeling implicit feedback, especially to alleviate exposure bias. Extensive experiments in three public real-world datasets demonstrate that EEDN outperforms state-of-the-art methods. Our source codes and data are released at https://github.com/WangXFng/EEDN
Xinfeng Wang, Jin Cui, Yoshimi Suzuki, Fumiyo Fukumoto. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2024.
Graph neural network (GNN)-based models have been extensively studied for recommendations, as they can extract high-order collaborative signals accurately which is required for high-quality recommender systems. However, they neglect the valuable information gained through negative feedback in two aspects: (1) different users might hold opposite feedback on the same item, which hampers optimal information propagation in GNNs, and (2) even when an item vastly deviates from users' preferences, they might still choose it and provide a negative rating. In this paper, we propose a negative feedback-aware recommender model (NFARec) that maximizes the leverage of negative feedback. To transfer information to multi-hop neighbors along an optimal path effectively, NFARec adopts a feedback-aware correlation that guides hypergraph convolutions (HGCs) to learn users' structural representations. Moreover, NFARec incorporates an auxiliary task - predicting the feedback sentiment polarity (i.e., positive or negative) of the next interaction - based on the Transformer Hawkes Process. The task is beneficial for understanding users by learning the sentiment expressed in their previous sequential feedback patterns and predicting future interactions. Extensive experiments demonstrate that NFARec outperforms competitive baselines. Our source code and data are released at https://github.com/WangXFng/NFARec.
Paraphrase identification has been one of the major topics in Natural Language Processing (NLP). However, how to interpret a diversity of contexts such as lexical and semantic information within a sentence as relevant features is still an open problem. This paper addresses the problem and presents an approach for leveraging contextual features with a neural-based learning model. Our Lexical, Syntactic, and Sentential Encodings (LSSE) learning model incorporates Relational Graph Convolutional Networks (R-GCNs) to make use of different features from local contexts, i.e., word encoding, position encoding, and full dependency structures. By utilizing the hidden states obtained by the R-GCNs as well as lexical and sentential encodings by Bidirectional Encoder Representations from Transformers (BERT), our model learns the contextual similarity between sentences effectively. The experimental results by using the two benchmark datasets, Microsoft Research Paraphrase Corpus (MRPC) and Quora Question Pairs (QQP) show that the improvement compared with the baseline, BERT sentential encodings model, was 1.7% F1-score on MRPC and 1.0% F1-score on QQP. Moreover, we verified that the combination of position encoding and syntactic features contributes to performance improvement.
Bayesian optimization (BO) is commonly used to optimize the hyperparameters of transfer learning models to improve the model’s performance significantly. In BO, the acquisition functions direct the hyperparameter space exploration during the optimization. However, the computational cost of evaluating the acquisition function and updating the surrogate model can become prohibitively expensive due to increasing dimensionality, making it more challenging to achieve the global optimum, particularly in image classification tasks. Therefore, this study investigates and analyses the effect of incorporating metaheuristic methods into BO to improve the performance of acquisition functions in transfer learning. By incorporating four different metaheuristic methods, namely Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC) Optimization, Harris Hawks Optimization, and Sailfish Optimization (SFO), the performance of acquisition function, Expected Improvement (EI), was observed in the VGGNet models for visual field defect multi-class classification. Other than EI, comparative observations were also conducted using different acquisition functions, such as Probability Improvement (PI), Upper Confidence Bound (UCB), and Lower Confidence Bound (LCB). The analysis demonstrates that SFO significantly enhanced BO optimization by increasing mean accuracy by 9.6% for VGG-16 and 27.54% for VGG-19. As a result, the best validation accuracy obtained for VGG-16 and VGG-19 is 98.6% and 98.34%, respectively.