Anmerkung: Intro -- Preface -- Organization -- Contents - Part III -- Recommender System -- Mixture of Graph Enhanced Expert Networks for Multi-task Recommendation -- 1 Introduction -- 2 The Proposed Method -- 2.1 Deep Interaction Context Exploitation with Multi-channel Graph Neural Network -- 2.2 Graph Enhanced Expert Network -- 2.3 Model Learning -- 2.4 Discussion -- 3 Experiments -- 3.1 Performance Comparison (RQ1) -- 3.2 Effect of the MGNN Module -- 3.3 Study of MoGENet -- 4 Conclusion -- References -- MF-TagRec: Multi-feature Fused Tag Recommendation for GitHub -- 1 Introduction -- 2 Related Work -- 2.1 Tag Recommendation -- 2.2 Tag Recommendation in Open-Source Communities -- 3 Method -- 3.1 Problem Formulation -- 3.2 Overview of MF-TagRec -- 3.3 CNN for Tag Prediction -- 3.4 Network Training Process -- 4 Experiments -- 4.1 Experimental Dataset -- 4.2 Evaluation Metrics -- 4.3 Experimental Settings -- 4.4 Experimental Results -- 5 Conclusions and Future Work -- References -- Co-contrastive Learning for Multi-behavior Recommendation -- 1 Introduction -- 2 Preliminaries -- 3 Methodology -- 3.1 Interactive View Encoder -- 3.2 Fold View Encoder -- 3.3 Divergence Constraint -- 3.4 Co-contrastive Learning -- 3.5 Efficient Joint Learning Without Sampling -- 4 Experiments -- 4.1 Datasets -- 4.2 Compared Models -- 4.3 Experimental Settings -- 4.4 Performance Comparison -- 4.5 Effectiveness Analysis on Data Sparsity Issue -- 4.6 Ablation Study -- 4.7 Parameter Sensitivity Analysis -- 5 Conclusion -- References -- Pattern Matching and Information-Aware Between Reviews and Ratings for Recommendation -- 1 Introduction -- 2 Related Work -- 3 The Proposed MIAN Model -- 3.1 Global Matching Module -- 3.2 Specific Matching Module -- 3.3 Information-Aware Layer -- 3.4 Interaction Aggregation Layer -- 3.5 Joint Learning of Review Matching and Rating Prediction. , 4 Experiments -- 4.1 Experimental Settings -- 4.2 Overall Performance (RQ1) -- 4.3 Ablation Experimental Study (RQ2) -- 4.4 Case Study (RQ3) -- 5 Conclusion -- References -- Cross-View Contrastive Learning for Knowledge-Aware Session-Based Recommendation -- 1 Introduction -- 2 Notations and Problem Statement -- 3 Method -- 3.1 View Generation -- 3.2 Dual-channel Graph View Encoder -- 3.3 Contrastive Learning and Recommendation -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Over Performance -- 4.3 Model Ablation Study -- 4.4 Handling Different Session Lengths -- 4.5 Hyperparameter Study -- 5 Conclusion -- References -- Reinforcement Learning -- HiSA: Facilitating Efficient Multi-Agent Coordination and Cooperation by Hierarchical Policy with Shared Attention -- 1 Introduction -- 2 Preliminaries and Related Work -- 2.1 Communicative Decentralized Partially Observable Markov Decision Process -- 2.2 Communicative Methods in MAS -- 2.3 Attention Mechanism -- 2.4 Hierarchical Policy with Attention -- 3 Method -- 3.1 Shared Attention Map for Communication -- 3.2 Hierarchical Structure with Shared Attention Mechanism -- 3.3 HiSA for Multi-agent Reinforcement Learning -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Experiments on the StarCraft Multi-Agent Challenge -- 4.3 Experiments on the Overcooked -- 5 Summary and Outlook -- References -- DDMA: Discrepancy-Driven Multi-agent Reinforcement Learning -- 1 Introduction -- 2 Related Work -- 3 Preliminary -- 3.1 Partially Observable Stochastic Game -- 3.2 Reinforcement Learning -- 4 Method -- 4.1 Initialization of the Multi-agent Policy -- 4.2 Focused Learning of the Multi-agent Policy -- 4.3 Training -- 5 Experiments -- 5.1 Collision Corridor -- 5.2 MPE Scenarios -- 5.3 Ablation Study -- 6 Conclusion -- References -- PRAG: Periodic Regularized Action Gradient for Efficient Continuous Control. , 1 Introduction -- 2 Background -- 3 From TD-Error to Action Gradient Error -- 3.1 TD-Error and TD-Learning -- 3.2 Action Gradient Error and Action Gradient Regularizer -- 3.3 Periodic Regularized Action Gradient Algorithm -- 4 Experiment -- 4.1 Overall Performance -- 4.2 Ablation Study -- 4.3 Parameter Study -- 5 Related Work -- 6 Conclusion -- References -- Identifying Multiple Influential Nodes for Complex Networks Based on Multi-agent Deep Reinforcement Learning -- 1 Introduction -- 2 Problem Formulation -- 3 Multi-agent Identification Framework -- 3.1 General Framework of MAIF -- 3.2 Framework Elements -- 3.3 Independent Actor-Critic Model -- 3.4 Counterfactual Multi-agent (COMA) Policy Gradients and Gate Recurrent Unit (GRU) Network -- 4 Experimental Preliminaries -- 4.1 Dataset -- 4.2 Comparison Method -- 4.3 Susceptible-Infected-Recovered (SIR) Model -- 5 Experimental Results -- 6 Conclusion -- References -- Online Learning in Iterated Prisoner's Dilemma to Mimic Human Behavior -- 1 Introduction -- 2 Related Work -- 3 Background -- 4 Experimental Setup -- 4.1 Iterated Prisoner's Dilemma (IPD) -- 4.2 Behavioral Cloning with Demonstration Rewards -- 4.3 Online Learning Agents -- 5 Results: Algorithms' Tournament -- 5.1 Multi-agent Tournament -- 6 Behavioral Cloning with Human Data -- 7 Clinical Evidences and Implications -- 8 Discussion -- 9 Conclusion -- References -- Optimizing Exploration-Exploitation Trade-off in Continuous Action Spaces via Q-ensemble -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 4 Proposed Method -- 4.1 Ensemble-Based Exploration Strategy -- 4.2 Selective Repeat Update -- 5 Experiments -- 5.1 Parameter Settings -- 5.2 Comparative Evaluation -- 5.3 Ablation Study -- 6 Conclusion -- References -- Hidden Information General Game Playing with Deep Learning and Search -- 1 Introduction -- 2 Background. , 2.1 General Game Playing -- 2.2 Generalised AlphaZero -- 2.3 Recursive Belief-Based Learning -- 3 Method -- 3.1 Propositional Networks for GDL-II -- 3.2 Sampling GDL-II States -- 3.3 CFR Search -- 3.4 Reinforcement Learning -- 4 Experiments -- 4.1 Evaluation Methodology -- 4.2 Results and Discussion -- 5 Conclusion and Future Work -- References -- Sequential Decision Making with ``Sequential Information'' in Deep Reinforcement Learning -- 1 Introduction -- 2 Related Work -- 3 Background -- 3.1 Deep Reinforcement Learning -- 3.2 Depthwise Separable Convolution -- 3.3 3D Temporal Convolution -- 4 Temporal Aggregation Network in DRL -- 5 Experiments -- 5.1 Experimental Setup -- 5.2 Results Analysis -- 6 Conclusion and Future Work -- References -- Two-Stream Communication-Efficient Federated Pruning Network -- 1 Introduction -- 2 Proposed Method -- 2.1 Preliminary -- 2.2 Downstream Compression via DRL Agent -- 2.3 Upstream Compression Based on Proximal Operator -- 3 Experimental Setup and Results -- 3.1 Compared Methods -- 3.2 Datasets and Simulation Settings -- 3.3 Experiment Results -- 3.4 Ablation Study -- 4 Conclusion -- References -- Strong General AI -- Multi-scale Lightweight Neural Network for Real-Time Object Detection -- 1 Introduction -- 2 Related Works -- 3 Methodology -- 3.1 Network Architecture -- 3.2 Fast Down-Sampling Module -- 3.3 Reduced Computational Block -- 3.4 Detection Part -- 4 Experiments -- 4.1 Experiments Setup -- 4.2 Results -- 4.3 Ablation Study -- 5 Conclusion -- References -- Hyperspectral Image Classification Based on Transformer and Generative Adversarial Network -- 1 Introduction -- 2 Related Works -- 2.1 Superpixelwise PCA -- 2.2 Auxiliary Classifier GANs -- 3 Proposed Method -- 3.1 The Framework of the Proposed SPCA-TransGAN -- 3.2 The Network Framework of Generator. , 3.3 The Network Framework of Multi-scale Discriminator -- 4 Experimental Results and Analysis -- 4.1 DataSets -- 4.2 Classification Results on Two Data Sets -- 5 Conclusion -- References -- Deliberation Selector for Knowledge-Grounded Conversation Generation -- 1 Introduction -- 2 Related Work -- 3 Approach -- 3.1 Problem Statement -- 3.2 Model Description -- 4 Experiments -- 4.1 Datasets -- 4.2 Evaluation Metrics -- 4.3 Baselines -- 4.4 Supplementary Details -- 4.5 Experimental Results -- 4.6 Ablation Test -- 4.7 Case Study -- 5 Conclusion -- References -- Training a Lightweight ViT Network for Image Retrieval -- 1 Introduction -- 2 Methodology -- 2.1 Knowledge Distillation with Relaxed Contrastive Loss -- 2.2 Quantized Heterogeneous Knowledge Distillation -- 2.3 Distillation Heterogeneous Quantization for Multi-exit Networks -- 3 Experiments -- 3.1 Experimental Setup -- 3.2 Comprehensive Comparison Results -- 3.3 Analysis of Distillation Quantization of Multi-exit Networks -- 4 Conclusions -- References -- Vision and Perception -- Segmented-Original Image Pairs to Facilitate Feature Extraction in Deep Learning Models -- 1 Introduction -- 2 Method -- 2.1 Datasets -- 2.2 Segmented-Original Image Pair Training Method -- 3 Experiments -- 3.1 Segmentation Algorithm -- 3.2 Classification Tasks -- 3.3 Unsupervised Learning Tasks -- 4 Conclusion -- References -- FusionSeg: Motion Segmentation by Jointly Exploiting Frames and Events -- 1 Introduction -- 2 Related Work -- 2.1 Motion Segmentation -- 2.2 Visual Transformer -- 3 Methodology -- 3.1 Input Representation -- 3.2 Network Architecture -- 3.3 Feature Fusion Method -- 3.4 Multi-Object Association -- 3.5 Feature Matching and Propagation -- 4 Experiment and Results -- 4.1 Implementation Details -- 4.2 Overview of Datasets -- 4.3 Discussion of Results -- 5 Conclusions and Future Work -- References. , Weakly-Supervised Temporal Action Localization with Multi-Head Cross-Modal Attention.