Abstract In video streaming, bandwidth constraints significantly affect client-side video quality. Addressing this, deep neural networks offer a promising avenue for implementing video super-resolution (VSR) at the user end, leveraging advancements in modern hardware, including mobile devices. The principal challenge in VSR is the computational intensity involved in processing temporal/spatial video data. Conventional methods, uniformly processing entire scenes, often result in inefficient resource allocation. This is evident in the over-processing of simpler regions and insufficient attention to complex regions, leading to edge artifacts in merged regions. Our innovative approach employs semantic segmentation and spatial frequency-based categorization to divide each video frame into regions of varying complexity: simple, medium, and complex. These are then processed through an efficient incremental model, optimizing computational resources. A key innovation is the sparse temporal/spatial feature transformation layer, which mitigates edge artifacts and ensures seamless integration of regional features, enhancing the naturalness of the super-resolution outcome. Experimental results demonstrate that our method significantly boosts VSR efficiency while maintaining effectiveness. This marks a notable advancement in streaming video technology, optimizing video quality with reduced computational demands. This approach, featuring semantic segmentation, spatial frequency analysis, and an incremental network structure, represents a substantial improvement over traditional VSR methodologies, addressing the core challenges of efficiency and quality in high-resolution video streaming.

In task-oriented dialogue systems, Dialogue State Tracking (DST) aims to extract users' intentions from the dialogue history. Currently, most existing approaches suffer from error propagation and are unable to dynamically select relevant information when utilizing previous dialogue states. Moreover, the relations between the updates of different slots provide vital clues for DST. However, the existing approaches rely only on predefined graphs to indirectly capture the relations. In this paper, we propose a Dialogue State Distillation Network (DSDN) to utilize relevant information of previous dialogue states and migrate the gap of utilization between training and testing. Thus, it can dynamically exploit previous dialogue states and avoid introducing error propagation simultaneously. Further, we propose an inter-slot contrastive learning loss to effectively capture the slot co-update relations from dialogue context. Experiments are conducted on the widely used MultiWOZ 2.0 and MultiWOZ 2.1 datasets. The experimental results show that our proposed model achieves the state-of-the-art performance for DST.

We consider the problem of imitation learning from suboptimal demonstrations that aims to learn a better policy than demonstrators. Previous methods usually learn a reward function to encode the underlying intention of the demonstrators and use standard reinforcement learning to learn a policy based on this reward function. Such methods can fail to control the distribution shift between demonstrations and the learned policy since the learned reward function may not generalize well on out-of-distribution samples and can mislead the agent to highly uncertain states, resulting in degenerated performance. To address this limitation, we propose a novel algorithm called Outperforming demonstrators by Directly Extrapolating Demonstrations(ODED). Instead of learning a reward function, ODED trains an ensemble of extrapolation networks that generate extrapolated demonstrations, i.e., demonstrations that may be induced by a good agent, based on provided demonstrations. With these extrapolated demonstrations, we can use an off-the-shelf imitation learning algorithm to learn a good policy. Guided by extrapolated demonstrations, the learned policy avoids visiting highly uncertain states and therefore controls the distribution shift. Empirically, we show that ODED outperforms suboptimal demonstrators and achieves better performance than state-of-the-art imitation learning algorithms on the MuJoCo and DeepMind Control Suite tasks.

Recently, spoken dialogue systems have been widely deployed in a variety of applications, serving a huge number of end-users. A common issue is that the errors resulting from noisy utterances, semantic misunderstandings, or lack of knowledge make it hard for a real system to respond properly, possibly leading to an unsatisfactory user experience. To avoid such a case, we consider a proactive interaction mechanism where the system predicts the user satisfaction with the candidate response before giving it to the user. If the user is not likely to be satisfied according to the prediction, the system will ask the user a suitable question to determine the real intent of the user instead of providing the response directly. With such an interaction with the user, the system can give a better response to the user. Previous models that predict the user satisfaction are not applicable to DuerOS which is a large-scale commercial dialogue system. They are based on hand-crafted features and thus can hardly learn the complex patterns lying behind millions of conversations and temporal dependency in multiple turns of the conversation. Moreover, they are trained and evaluated on the benchmark datasets with adequate labels, which are expensive to obtain in a commercial dialogue system. To face these challenges, we propose a pipeline to predict the user satisfaction to help DuerOS decide whether to ask for clarification in each turn. Specifically, we propose to first generate a large number of weak labels and then train a transformer-based model to predict the user satisfaction with these weak labels. Moreover, we propose a metric, contextual user satisfaction, to evaluate the experience under the proactive interaction mechanism. At last, we deploy and evaluate our model on DuerOS, and observe a 19% relative improvement on the accuracy of user satisfaction prediction and 2.3% relative improvement on user experience.

The cross-lingual sentiment analysis (CLSA) aims to leverage label-rich resources in the source language to improve the models of a resource-scarce domain in the target language, where monolingual approaches based on machine learning usually suffer from the unavailability of sentiment knowledge. Recently, the transfer learning paradigm that can transfer sentiment knowledge from resource-rich languages, for example, English, to resource-poor languages, for example, Chinese, has gained particular interest. Along this line, in this article, we propose semisupervised learning with SCL and space transfer (ssSCL-ST), a semisupervised transfer learning approach that makes use of structural correspondence learning as well as space transfer for cross-lingual sentiment analysis. The key idea behind ssSCL-ST, at a high level, is to explore the intrinsic sentiment knowledge in the target-lingual domain and to reduce the loss of valuable knowledge due to the knowledge transfer via semisupervised learning. ssSCL-ST also features in pivot set extension and space transfer, which helps to enhance the efficiency of knowledge transfer and improve the classification accuracy in the target language domain. Extensive experimental results demonstrate the superiority of ssSCL-ST to the state-of-the-art approaches without using any parallel corpora.

Recently, the graph neural network (GNN) has shown great power in matrix completion by formulating a rating matrix as a bipartite graph and then predicting the link between the corresponding user and item nodes. The majority of GNN-based matrix completion methods are based on Graph Autoencoder (GAE), which considers the one-hot index as input, maps a user (or item) index to a learnable embedding, applies a GNN to learn the node-specific representations based on these learnable embeddings and finally aggregates the representations of the target users and its corresponding item nodes to predict missing links. However, without node content (i.e., side information) for training, the user (or item) specific representation can not be learned in the inductive setting, that is, a model trained on one group of users (or items) cannot adapt to new users (or items). To this end, we propose an inductive matrix completion method using GAE (IMC-GAE), which utilizes the GAE to learn both the user-specific (or item-specific) representation for personalized recommendation and local graph patterns for inductive matrix completion. Specifically, we design two informative node features and employ a layer-wise node dropout scheme in GAE to learn local graph patterns which can be generalized to unseen data. The main contribution of our paper is the capability to efficiently learn local graph patterns in GAE, with good scalability and superior expressiveness compared to previous GNN-based matrix completion methods. Furthermore, extensive experiments demonstrate that our model achieves state-of-the-art performance on several matrix completion benchmarks.

Abstract With the increasingly extensive applications of the network, the security of internal network of enterprises is facing more and more threats from the outside world, which implies the importance to master the network risk assessment skills. To improve the accuracy is an importent issue. In the big data era, there are various security protection techniques and different types of group data. Meanwhile, Online Social Networks (OSNs) and Social Internet of Things (SIoT) are becoming popular patterns of meeting people and keeping in touch with friends (Jiang et al. ACM Comput Surv 49:10:1–10:35 2016; Shen et al. 2017). Risk assessment, as a bridge between security experts and network administrators, whose accuracy can influence the judgment of administrators to the entire network state. In order to solve this problem, this essay uses the Baum Welch algorithm to optimize the risk assessment process by establishing the HMM model, which can improve the accuracy of the evaluation value. Firstly, behavior of the attacker is described in-depth by the attack graph generated through MulVAL framework. Then, the nodes on the attack path can will be evaluated and the value will be further evaluated by the Bayesian model. Finally, by establishing the hidden Markov model, the corresponding parameters can be defined and the most likely probabilistic state transition sequence can be calculated by using the Viterbi algorithm and Baum Welch algorithm to deduce the attack intent with the highest possibility.

In mobile crowdsourcing (MCS), the platform selects participants to complete location-aware tasks from the recruiters aiming to achieve multiple goals (e.g., profit maximization, energy efficiency, and fairness). However, different MCS systems have different goals and there are possibly conflicting goals even in one MCS system. Therefore, it is crucial to design a participant selection algorithm that applies to different MCS systems to achieve multiple goals. To deal with this issue, we formulate the participant selection problem as a reinforcement learning problem and propose to solve it with a novel method, which we call auxiliary-task based deep reinforcement learning (ADRL). We use transformers to extract representations from the context of the MCS system and a pointer network to deal with the combinatorial optimization problem. To improve the sample efficiency, we adopt an auxiliary-task training process that trains the network to predict the imminent tasks from the recruiters, which facilitates the embedding learning of the deep learning model. Additionally, we release a simulated environment on a specific MCS task, the ride-sharing task, and conduct extensive performance evaluations in this environment. The experimental results demonstrate that ADRL outperforms and improves sample efficiency over other well-recognized baselines in various settings.