Information retrieval (IR) systems play a critical role in navigating information overload across various applications. Existing IR benchmarks primarily focus on simple queries that are semantically analogous to single- and multi-hop relations, overlooking complex logical queries involving first-order logic operations such as conjunction (∧), disjunction (∨), and negation (¬). Thus, these benchmarks can not be used to sufficiently evaluate the performance of IR models on complex queries in real-world scenarios. To address this problem, we propose a novel method leveraging large language models (LLMs) to construct a new IR dataset ComLQ for Complex Logical Queries, which comprises 2,909 queries and 11,251 candidate passages. A key challenge in constructing the dataset lies in capturing the underlying logical structures within unstructured text. Therefore, by designing the subgraph-guided prompt with the subgraph indicator, an LLM (such as GPT-4o) is guided to generate queries with specific logical structures based on selected passages. All query-passage pairs in ComLQ are ensured structure conformity and evidence distribution through expert annotation. To better evaluate whether retrievers can handle queries with negation, we further propose a new evaluation metric, Log-Scaled Negation Consistency (LSNC@K). As a supplement to standard relevance-based metrics (such as nDCG and mAP), LSNC@K measures whether top-K retrieved passages violate negation conditions in queries. Our experimental results under zero-shot settings demonstrate existing retrieval models' limited performance on complex logical queries, especially on queries with negation, exposing their inferior capabilities of modeling exclusion. In summary, our ComLQ offers a comprehensive and fine-grained exploration, paving the way for future research on complex logical queries in IR.

Federated learning (FL) is greatly challenged by the communication bottleneck and computation limitation on clients. Existing methods based on quantization for FL cannot simultaneously reduce the uplink and downlink communication cost and mitigate the computation burden on clients. To address this problem, in this paper, we propose the first low-bit integerized federated learning (LBI-FL) framework that quantizes the weights, activations, and gradients to lower than INT8 precision to evidently reduce the communication and computational costs. Specifically, we achieve dynamical temporal bit-width allocation for weights, activations, and gradients along the training trajectory via reinforcement learning. An agent is trained to determine bit-width allocation by comprehensively considering the states like current bit-width, training stage, and quantization loss as the state. The agent efficiently trained on small-scale datasets can be well generalized to train varying network architectures on non-independent and identically distributed datasets. Furthermore, we demonstrated in theory that federated learning with gradient quantization achieves an equivalent convergence rate to FedAvg. The proposed LBI-FL can reduce the communication costs by 8 times compared to full-precision FL. Extensive experiments show that the proposed LBI-FL achieves a reduction of more than 50\% BitOPs per client on average for FL with less than 2\% accuracy loss compared to low-bit training with INT8 precision.

The significant communication overhead and client data heterogeneity have posed an important challenge to current federated learning (FL) paradigm. Existing compression-based and optimization-based FL algorithms typically focus on addressing either the model compression challenge or the data heterogeneity issue individually, rather than tackling both of them. In this paper, we observe that by symbolizing the client model updates to be uploaded (i.e., normalizing the magnitude for each model parameter at local clients), the model heterogeneity, essentially stemmed from data heterogeneity, can be mitigated, and thereby helping improve the overall generalization performance of the globally aggregated model at the server. Inspired with this observation, and further motivated by the success of Lion optimizer in achieving the optimal performance on most tasks in the centralized learning, we propose a new FL algorithm, called FedSMU, which simultaneously reduces the communication overhead and alleviates the data heterogeneity issue. Specifically, FedSMU splits the standard Lion optimizer into the local updates and global execution, where only the symbol of client model updates commutes between the client and server. We theoretically prove the convergence of FedSMU for the general non-convex settings. Through extensive experimental evaluations on several benchmark datasets, we demonstrate that our FedSMU algorithm not only reduces the communication overhead, but also achieves a better generalization performance than the other compression-based and optimization-based baselines.

ABSTRACT Renal CT images contain complex spatial volumetric information, and deep learning models have difficulty learning consistent features from images with different voxel spacing, resulting in suboptimal segmentation performance for kidney tumors. We have introduced a modified deep learning model called RAScU‐Net to address these challenges. The RAScU‐Net adopts a coarse‐to‐fine segmentation strategy and a novel voxel spacing unification method to segment renal regions while preserving CT image data. The residual asymmetric self‐calibration (RASc) and residual self‐calibration (ResSc) modules are designed to capture feature information from CT images with different voxel spacings, thereby establishing long‐range dependencies. Finally, the innovative Channel Attention Gate (CAG) module generates attention maps from multiple perspectives, facilitating the integration of high‐ and low‐level features. The experimental results demonstrate that the RAScU‐Net significantly surpasses existing kidney tumor segmentation networks, achieving Dice scores of 0.882 and 0.877 for tumor segmentation of KiTS19 and KiTS21, respectively.

This paper investigates the attitude tracking control problem for spacecraft. A tanh-type self-learning control (TSLC) approach with variable learning intensity (VLI) is proposed, which avoids saturation while overcoming previous algorithms’ long response time disadvantage. Unlike the previously introduced VLI method, the enhanced TSLC does not tweak the learning intensity based on the previous controller output. Instead, it relates learning intensity to an intermediate variable directly related to the system state and tunes the learning intensity using a tanh-type function. Since the system state reflects the tracking error in real-time, the transformed tanh-type function has a higher decay rate than the exponential function, which not only significantly reduces the saturation response but also improves the response speed and achieves higher steady-state accuracy. Simulation proved TSLC’s superiority, considering adverse actuator factors such as dead zone, bias torque, and saturation. The proposed approach has also been validated on the Quanser helicopter platform, confirming its better performance.

The cut-in behavior of adjacent vehicles presents a challenge for the Adaptive Cruise Control (ACC) system. Inability to proactively discern adjacent vehicles’ cut-in actions could impact driving safety. In addition, abrupt changes in ego vehicle’s following target might provoke excessive reactions, undermining passenger comfort. To address this challenge, this paper integrates trajectory prediction model into a deep reinforcement learning(DRL)-based car-following policy. Utilizing Finite State Machine(FSM), we proactively identify cut-in vehicles based on the predicted trajectories to enhance safety. In designing the DRL-based car-following policy, we propose a novel reward function by analyzing human driving data distribution and considering lateral information of cut-in vehicles. This method enhances driving comfort by significantly reducing abrupt maneuvers in both car-following and cut-in scenarios. Additionally, we investigate the impact of state observation configurations on the performance of the DRL policy. Our experimental findings reveal that incorporating the ego vehicle’s acceleration into the observation state contributes to optimizing comfort and enhancing robustness in scenarios where the observation of other vehicles’ motion state is not precise.

As an active network security protection scheme, intrusion detection system (IDS) undertakes the important responsibility of detecting network attacks in the form of malicious network traffic. Intrusion detection technology is an important part of IDS. At present, many scholars have carried out extensive research on intrusion detection technology. However, developing an efficient intrusion detection method for massive network traffic data is still difficult. Since Generative Adversarial Networks (GANs) have powerful modeling capabilities for complex high-dimensional data, they provide new ideas for addressing this problem. In this paper, we put forward an EBGAN-based intrusion detection method, IDS-EBGAN, that classifies network records as normal traffic or malicious traffic. The generator in IDS-EBGAN is responsible for converting the original malicious network traffic in the training set into adversarial malicious examples. This is because we want to use adversarial learning to improve the ability of discriminator to detect malicious traffic. At the same time, the discriminator adopts Autoencoder model. During testing, IDS-EBGAN uses reconstruction error of discriminator to classify traffic records.

Mini-batch Gradient Descent (MGD) has become a standard for deep learning model training. For a long period of time, the size of the mini-batch (also known as batch size) is set empirically as a fixed value, while recent works have demonstrated it could have crucial effects on the training. Although there already exist several adaptive batch size methods, they either add significant overhead to the training, or lack of robustness on various training scenarios. In this work, an adaptive batch size method to accelerate MGD training is proposed, whose basic idea is to concurrently run training with two batch sizes, and choose batch size based on the comparison of the evaluated history performance. It can be easily implemented on various deep learning platforms, and the experiment results suggest that the proposed method achieves high performance and strong robustness with acceptable and controllable overhead, which outperforms existing adaptive batch size methods.