6 April 2023 in IEEE Transactions on Neural Networks and Learning Systems
Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks. However, most existing pruning approaches are driven by empirical heuristics and rarely consider the joint impact of channels, leading to unguaranteed and suboptimal performance. In this article, we propose a novel channel pruning method via class-aware trace ratio optimization () to reduce the computational burden and accelerate the model inference. Utilizing class information from a few samples, measures the joint impact of multiple channels by feature space discriminations and consolidates the layerwise impact of preserved channels. By formulating channel pruning as a submodular set function maximization problem, solves it efficiently via a two-stage greedy iterative optimization procedure. More importantly, we present theoretical justifications on convergence of and performance of pruned networks. Experimental results demonstrate that achieves higher accuracy with similar computation cost or lower computation cost with similar accuracy than other state-of-the-art channel pruning algorithms. In addition, because of its class-aware property, is suitable to prune efficient networks adaptively for various classification subtasks, enhancing handy deployment and usage of deep networks in real-world applications.
2 October 2019 in IEEE Transactions on Neural Networks and Learning Systems
The architecture of convolutional neural networks (CNNs) is a key factor of influencing their performance. Although deep CNNs perform well in many difficult problems, how to intelligently design the architecture is still a challenging problem. Focusing on two practical architectural design problems: to maximize the accuracy with a given forward running time and to minimize the forward running time with a given accuracy requirement, we innovatively utilize prior knowledge to convert architecture optimization problems into submodular optimization problems. We propose efficient Greedy algorithms to solve them and give theoretical bounds of our algorithms. Specifically, we employ the techniques on some public data sets and compare our algorithms with some other hyperparameter optimization methods. Experiments show our algorithms' efficiency.
2 September 2022 in IEEE Transactions on Intelligent Transportation Systems
With millions of people using ride-hailing platforms for daily travel, estimated time of arrival (ETA) has become a significant problem in intelligent transportation systems and attracted considerable attention recently. Deep learning-based ETA methods have achieved promising results using massive spatial-temporal data. However, we find that the prediction accuracy is not satisfactory in practical applications due to the prevalent data sparsity problems. Instead of focusing on the average prediction performance as many other methods, this study aims to alleviate the data sparsity problems in ETA to enhance user experience. In general, the data sparsity problems arise from two aspects. The first is the road network, where many links are only traversed by few floating cars. The second aspect is drivers, where many drivers’ trajectories are too scarce (e.g., with only 3 trip records). To alleviate the sparsity in road network, we propose a Road Network Metric Learning framework for ETA (), where an auxiliary metric learning task is used to improve the link-embedding, especially for links with insufficient data. A novel triangle loss is proposed to improve metric learning effectiveness for links. Experiments on massive real-world data show that outperforms competing methods by promoting the cold links with limited data. Furthermore, we propose a novel unified framework to Alleviate Data Sparsity problems in ETA () by extending with an additional auxiliary task for driver ID embedding. Results with extensive experiments demonstrate that can effectively alleviate the data sparsity problems caused by road network and driver sparsity.
21 June 2021 in IEEE Signal Processing Letters
Deep convolutional neural networks have achieved great success in many computer vision tasks. However, they can be attacked by adversarial examples which are input-data with small intentional feature perturbations to fool machine learning models. This vulnerability to adversarial examples poses a potential threat to their widespread application, especially in securitysensitive scenarios. In this paper, we revisit adversarial examples in the frequency domain referring to the computational theory of edge detection, and propose a novel densely high-frequency convolution neural network (DiFNet) to effectively defend against adversarial attacks. DiFNet introduces classical edge detection operations into the network structure to enhance the detection ability for high-frequency components in the image. It works well to defend against the imperceptible perturbations attacks even without adversarial examples. Experiments demonstrate that DiFNet outperforms handcraft-designed CNNs in terms of prediction accuracy with improved robustness against state-ofthe- art adversarial attacks (FGSM, PGD, etc.).
27 May 2021 in IEEE Signal Processing Letters
The next-item recommendation has been in the central of interest in real-world applications such as e-commerce. However, it is challenging to infer what a user may purchase next due the complex interactions in the historical sessions and the changing semantics of an item over time. Most existing methods employ separate models to generate the general preference and the sequential patterns for the next-item recommendation without considering the interactions between the two factors or use a simple linear combination of the two factors. In this paper, we propose a deep adaptable co-embedding neural network (ACENet) to address these limitations. ACENet not only adaptably balances the combination of general preference and sequential patterns but also introduces dynamic attention for each factor in hybrid representations. Extensive experiments on two real-world datasets show the superiority of ACENet compared with other state-of-the-art methods.