Malicious social bots pose a serious threat to social network security by spreading false information and guiding bad opinions in social networks. The singularity and scarcity of single organization data and the high cost of labeling social bots have given rise to the construction of federated models that combine federated learning with social bot detection. In this paper, we first combine the federated learning framework with the Relational Graph Convolutional Neural Network (RGCN) model to achieve federated social bot detection. A class-level cross entropy loss function is applied in the local model training to mitigate the effects of the class imbalance problem in local data. To address the data heterogeneity issue from multiple participants, we optimize the classical federated learning algorithm by applying knowledge distillation methods. Specifically, we adjust the client-side and server-side models separately: training a global generator to generate pseudo-samples based on the local data distribution knowledge to correct the optimization direction of client-side classification models, and integrating client-side classification models’ knowledge on the server side to guide the training of the global classification model. We conduct extensive experiments on widely used datasets, and the results demonstrate the effectiveness of our approach in social bot detection in heterogeneous data scenarios. Compared to baseline methods, our approach achieves a nearly 3–10% improvement in detection accuracy when the data heterogeneity is larger. Additionally, our method achieves the specified accuracy with minimal communication rounds.

Neural networks provide new possibilities to uncover semantic relationships between words by involving contextual information, and further a way to learn the matching pattern from document-query word contextual similarity matrix, which has brought promising results in IR. However, most neural IR methods rely on the conventional word-word matching framework for finding a relevant document for a query. Its effect is limited due to the wide gap between the lengths of query and document. To address this problem, we propose a salient context-based semantic matching (SCSM) method to build a bridge between query and document. Our method locates the most relevant context in the document using a shifting window with adapted length and then calculates the relevance score within it as the representation of the document. We define the notion of contextual salience and the corresponding measures to calculate the relevance of a context to a given query, in which the interaction between the query and the context is modeled by semantic similarity. Experiments on various collections from TREC show the effectiveness of our model as compared to the state-of-the-art methods.

Serving the ever-growing demand for computation, storage, and networking resources for multi-tenant in cloud computing is an important mission of Data Center Networks (DCNs). In this paper, we study the dynamic request updating problem, and our objective is to maximize the elasticity of cloud-based DCNs while achieving rapid response to multi-tenants. We use virtual clusters under the hose communication model to denote requests. Instead of using heuristic algorithms as the existing work does, this paper introduces a novel two-stage dynamic request updating framework with elastic resource scheduling strategy. In the first stage, we propose a multi-tenant fast initial provisioning scheme to realize the real-time response and analyze its optimality and complexity. Additionally, we provide a deep reinforcement learning-based dynamic updating strategy to enhance the elasticity of virtual clusters that are being used or scaling during the second stage. We train a fully connected neural network by creating a new feasible action set to realize the reduction, and it approximates the policy based on a proposed aggressive objective selection method to improve training speed while avoiding high dimensions caused by large scales of tenants and DCNs. Extensive evaluations demonstrate that our scheme outperforms baselines in terms of both elasticity and efficiency.

In this paper, we propose a salient-context based semantic matching method to improve relevance ranking in information retrieval. We first propose a new notion of salient context and then define how to measure it. Then we show how the most salient context can be located with a sliding window technique. Finally, we use the semantic similarity between a query term and the most salient context terms in a corpus of documents to rank those documents. Experiments on various collections from TREC show the effectiveness of our model compared to the state-of-the-art methods.

Current deformation perception methods for soft robots primarily rely on external vision systems, which exhibit limited adaptability. To overcome this limitation, this study proposes a self-sensing approach that enables soft robots to perceive deformation using their own electric potential differences, eliminating reliance on external devices. The proposed method consists of two key components: a deformation data acquisition strategy based on Coupling Field Simulation (CFS), and a predictive model trained using a Gated Recurrent Unit (GRU) neural network. The CFS-based method builds upon prior work, where CFS models were successfully applied to capacitive sensors on soft manipulators. In this study, we extend this framework to design a GRU-based prediction system, train the GRU model with Adam optimization to learn the nonlinear deformation-electric signal mapping. This integrated approach ultimately yields a deformation prediction model with enhanced accuracy through multi-physics data synthesis and iterative parameter adjustment. The model achieved a low mean squared error and good robustness during testing. This closed-loop self-sensing framework offers a promising alternative to vision-dependent approaches, potentially enhancing soft robot autonomy and adaptive control in complex environments.