Chih-Yi Chiu

Munlika Rattaphun, Wen-Chieh Fang, Chih-Yi Chiu

In this study, we present a novel clustering-based collaborative filtering (CF) method for recommender systems. Clustering-based CF methods can effectively deal with data sparsity and scalability problems. However, most of them are applied to a single representation space, which might not characterize complex user-item interactions well. We argue that the user-item interactions should be observed from multiple views and characterized in an adaptive way. To address this issue, we leveraged the global and local properties to construct multiple representation spaces by learning various training datasets and loss functions. An attention network was built to generate a blended representation according to the relative importance of the representation spaces for each user-item pair, providing a flexible way to characterize diverse user-item interactions. Substantial experiments were evaluated on four popular benchmark datasets. The results show that the proposed method is superior to several CF methods where only one representation space is considered.

Sarawut Markchit, Chih-Yi Chiu

To overcome the barrier of storage and computation, the hashing technique has been widely used for nearest neighbor search in multimedia retrieval applications recently. Particularly, cross-modal retrieval that searches across different modalities becomes an active but challenging problem. Although dozens of cross-modal hashing algorithms are proposed to yield compact binary codes, the exhaustive search is impractical for the real-time purpose, and Hamming distance computation suffers inaccurate results. In this paper, we propose a novel search method that utilizes a probability-based index scheme over binary hash codes in cross-modal retrieval. The proposed hash code indexing scheme exploits a few binary bits of the hash code as the index code. We construct an inverted index table based on index codes and train a neural network to improve the indexing accuracy and efficiency. Experiments are performed on two benchmark datasets for retrieval across image and text modalities, where hash codes are generated by three cross-modal hashing methods. Results show the proposed method effectively boost the performance on these hash methods.

Chih-Yi Chiu, Amorntip Prayoonwong, Yin-Chih Liao

In this study, we present a novel ranking model based on learning neighborhood relationships embedded in the index space. Given a query point, conventional approximate nearest neighbor search calculates the distances to the cluster centroids, before ranking the clusters from near to far based on the distances. The data indexed in the top-ranked clusters are retrieved and treated as the nearest neighbor candidates for the query. However, the loss of quantization between the data and cluster centroids will inevitably harm the search accuracy. To address this problem, the proposed model ranks clusters based on their nearest neighbor probabilities rather than the query-centroid distances. The nearest neighbor probabilities are estimated by employing neural networks to characterize the neighborhood relationships, i.e., the density function of nearest neighbors with respect to the query. The proposed probability-based ranking can replace the conventional distance-based ranking for finding candidate clusters, and the predicted probability can be used to determine the data quantity to be retrieved from the candidate cluster. Our experimental results demonstrated that the proposed ranking model could boost the search performance effectively in billion-scale datasets.

Yi-Min Chou, Yi-Ming Chan, Jia-Hong Lee et al.

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks and merges them into a unified model by sharing the representative codes of weights. The shared weights are further re-trained to fine-tune the performance of the merged model. The proposed method effectively produces a compact model that may run original tasks simultaneously on resource-limited devices. As it preserves the general architectures and leverages the co-used weights of well-trained networks, a substantial training overhead can be reduced to shorten the system development time. Experimental results demonstrate a satisfactory performance and validate the effectiveness of the method.