Unsupervised Graph Domain Adaptation (UGDA) seeks to bridge distribution shifts between domains by transferring knowledge from labeled source graphs to given unlabeled target graphs. Existing UGDA methods primarily focus on aligning features in the latent space learned by graph neural networks (GNNs) across domains, often overlooking structural shifts, resulting in limited effectiveness when addressing structurally complex transfer scenarios. Given the sensitivity of GNNs to local structural features, even slight discrepancies between source and target graphs could lead to significant shifts in node embeddings, thereby reducing the effectiveness of knowledge transfer. To address this issue, we introduce a novel approach for UGDA called Target-Domain Structural Smoothing (TDSS). TDSS is a simple and effective method designed to perform structural smoothing directly on the target graph, thereby mitigating structural distribution shifts and ensuring the consistency of node representations. Specifically, by integrating smoothing techniques with neighbor- hood sampling, TDSS maintains the structural coherence of the target graph while mitigating the risk of over-smoothing. Our theoretical analysis shows that TDSS effectively reduces target risk by improving model smoothness. Empirical results on three real-world datasets demonstrate that TDSS outperforms recent state-of-the-art baselines, achieving significant improvements across six transfer scenarios.

To address the challenge of scarce computational resources in genomic modeling, we introduce GERM, a genomic foundation model optimized for accessibility and adaptability. GERM improves upon models like DNABERT-2 by eliminating outliers that hinder low-rank adaptation and post-training quantization, enhancing both efficiency and robustness. We replace the vanilla attention layer with an outlier-free mechanism inspired by associative memory models. By removing outliers during both pre-training and fine-tuning, this approach accelerates adaptation, reduces computational costs, and enhances quantization robustness within acceptable loss margins. Additionally, we propose GERM-T, a strategy that employs small-step continual learning within the outlier-free framework, leveraging original checkpoints to avoid retraining from scratch. Empirically, GERM improves fine-tuning performance by 37.98% and quantization by 64.34% over the baseline model. It also reduces average kurtosis by 92.14% and maximum infinity norm by 82.77%. Compared to leading methods, GERM consistently delivers superior performance, offering a practical solution for genomic modeling in resource-constrained settings.

We propose a new system named DOS®(Deployment Operating System for Robots) for reliably deploying any data-driven robots in both production and simulation environments. Compared to existing systems, DOS®features a unique CI/CD (continuous integration and continuous deployment) architecture which allows us to seamlessly integrate agile development and reliable operation in a fully automated fashion. With this CI/CD architecture, this paper mainly introduces three essential components that uniquely differentiate DOS®from existing robotic systems: (i) An environment adapter that provides a systematic and robust approach to handle the deployment complexity in real world environments; (ii) A data replay reservoir that provides a unified data model supporting arbitrary robotic decision models; (iii) An analytical profiler that collects any set of user-defined performance metrics for system optimization. DOS®significantly increases the reliability and maintainability of the deployed robotic systems. To illustrate this point, we compare DOS®with more traditional approaches on deploying a navigational robot in a challenging working environment with many new corner case scenarios. Our results show that DOS®outperforms traditional approach in great magnitudes in terms of deployment time and operational robustness.

This paper considers the problem of learning from multiple sets of inaccurate labels, which can be easily obtained from low-cost annotators, such as rule-based annotators. Previous works typically concentrate on aggregating information from all the annotators, overlooking the significance of data refinement. This paper presents a collaborative refining approach for learning from inaccurate labels. To refine the data, we introduce the annotator agreement as an instrument, which refers to whether multiple annotators agree or disagree on the labels for a given sample. For samples where some annotators disagree, a comparative strategy is proposed to filter noise. Through theoretical analysis, the connections among multiple sets of labels, the respective models trained on them, and the true labels are uncovered to identify relatively reliable labels. For samples where all annotators agree, an aggregating strategy is designed to mitigate potential noise. Guided by theoretical bounds on loss values, a sample selection criterion is introduced and modified to be more robust against potentially problematic values. Through these two methods, all the samples are refined during training, and these refined samples are used to train a lightweight model simultaneously. Extensive experiments are conducted on benchmark and real-world datasets to demonstrate the superiority of our methods.

The rapid development of graph neural networks (GNNs) encourages the rising of link prediction, achieving promising performance with various applications. Unfortunately, through a comprehensive analysis, we surprisingly find that current link predictors with dynamic negative samplers (DNSs) suffer from the migration phenomenon between ''easy'' and ''hard'' samples, which goes against the preference of DNS of choosing "hard" negatives, thus severely hindering capability. Towards this end, we propose the MeBNS framework, serving as a general plugin that can potentially improve current negative sampling based link predictors. In particular, we elaborately devise a Meta-learning Supported Teacher-student GNN (MST-GNN) that is not only built upon teacher-student architecture for alleviating the migration between ''easy'' and ''hard'' samples but also equipped with a meta learning based sample re-weighting module for helping the student GNN distinguish ''hard'' samples in a fine-grained manner. To effectively guide the learning of MST-GNN, we prepare a Structure enhanced Training Data Generator (STD-Generator) and an Uncertainty based Meta Data Collector (UMD-Collector) for supporting the teacher and student GNN, respectively. Extensive experiments show that the MeBNS achieves remarkable performance across six link prediction benchmark datasets.

Time delay integration charge-coupled device (TDI CCD) is sensitive to the platform’s stability during push-broom imaging. Due to variations in total integration time, panchromatic and multispectral images suffer varying degrees of geometric distortion caused by satellite jitter with high frequency, which leads to different inner distortion in different band images and different band-to-band mismatching errors between different band combinations. To address this problem, this paper proposes a rigorous parallax observation model considering multi-stage integration time and presents a jitter distortion correction method for remote sensing panchromatic and multispectral images captured by TDI cameras based on it. First, the law of the amplitude attenuation and phase offset of platform jitter deviation on the image under different TDI stages is determined through simulation verification. Then, the rigorous parallax observation model is proposed to establish an accurate relationship between the relative jitter error of two multispectral images with multi-stage integration and the absolute single-stage integration jitter error by introducing the amplitude attenuation factor and phase offset. Finally, the jitter distortion curves of images with different integration stages and integration time can be reconstructed based on the estimated absolute jitter error and the imaging parameters. Subsequently, the jitter distortion can be further corrected by image resampling. The proposed method was verified through both simulation and real data experiments using GaoFen-9 satellite images. Experimental results show that the proposed method can effectively correct high-frequency jitter distortion in panchromatic and multispectral images, which cannot be corrected by traditional single-stage integration jitter detection model.

We propose EMS®, a cloud-enabled massive computational experiment management system supporting high-throughput computational robotics research. Compared to existing systems, EMS® features a sky-based pipeline orchestrator which allows us to exploit heterogeneous computing environments painlessly (e.g., on-premise clusters, public clouds, edge devices) to optimally deploy large-scale computational jobs (e.g., with more than millions of computational hours) in an integrated fashion. Cornerstoned on this sky-based pipeline orchestrator, this paper introduces three abstraction layers of the EMS® software architecture: (i) Configuration management layer focusing on automatically enumerating experimental configurations; (ii) Dependency management layer focusing on managing the complex task dependencies within each experimental configuration; (iii) Computation management layer focusing on optimally executing the computational tasks using the given computing resource. Such an architectural design greatly increases the scalability and reproducibility of data-driven robotics research leading to much-improved productivity. To demonstrate this point, we compare EMS® with more traditional approaches on an offline reinforcement learning problem for training mobile robots. Our results show that EMS® outperforms more traditional approaches in two magnitudes of orders (in terms of experimental high throughput and cost) with only several lines of code change. We also exploit EMS® to develop mobile robot, robot arm, and bipedal applications, demonstrating its applicability to numerous robot applications.

In this paper, we introduce a robotic agent specifically designed to analyze external environments and address participants’ questions. The primary focus of this agent is to assist individuals using language-based interactions within video-based scenes. Our proposed method integrates video recognition technology and natural language processing models within the robotic agent. We investigate the crucial factors affecting human-robot interactions by examining pertinent issues arising between participants and robot agents. Methodologically, our experimental findings reveal a positive relationship between trust and interaction efficiency. Furthermore, our model demonstrates a 2% to 3% performance enhancement in comparison to other benchmark methods.

Although time delay integration charge-coupled devices (TDI CCDs) have been widely used in high-resolution spaceborne optical cameras, they are sensitive to satellite jitter: the images obtained by them are affected by both distortion and blur. Therefore, according to the multistage integral imaging characteristics of TDI CCDs, this article not only proposes a continue dynamic shooting model (CDSM) to reflect the real push-broom mode of the satellite but also presents a method containing jitter detection and image restoration based on it. In the presented method, the CDSM subdivides the TDI CCD integration intervals. The subdivision number of CDSM is determined by the proposed integral transformation function (ITF). Then, it feeds back into the ITF and also contributes to the point spread function (PSF) estimation. Among the abovementioned, ITF defines the relationship between the parallax images and the jitter curve, and aims to improve the jitter detection performance. Finally, an adaptive image restoration based on context is conducted, which combines time, space, and spectrum information. Besides the simulated images, multispectral images of GaoFen-1 02 satellite were also adopted to validate the performance of the presented method. Experimental results indicate that the accuracy of the jitter detection is increased, and the geometric and radiometric qualities of restored images are also improved.

We exploit Markov games as a framework for collision-free navigation of human-centered robots. Unlike the classical methods which formulate robot navigation as a single-agent Markov decision process with a static environment, our framework of Markov games adopts a multi-agent formulation with one primary agent representing the robot and the remaining auxiliary agents form a dynamic or even competing environment. Such a framework allows us to develop a path-following type adversarial training strategy to learn a robust decentralized collision avoidance policy. Through thorough experiments on both simulated and real-world mobile robots, we show that the learnt policy outperforms the state-of-the-art algorithms in both sample complexity and runtime robustness.

From a senior person's daily activities, one can tell a lot about the health condition of the senior person. Thus we believe that senior home activity analysis will play an important role in the health care of senior people. Toward this goal, we propose a senior home activity summary system. One challenging problem in such a real world application is that senior's activities are usually accompanied by nurse's walking. It is impractical to predefine and label all the potential activities of all the potential visitors. To address this problem, we propose a novel feature filtering technique to reduce or eliminate the effects of the interest points that belong to other people. To evaluate the proposed activity summary system, we have collected a senior home activity dataset (SAR), and performed activity recognition for eating and walking classes. The experimental results show that the proposed system provides quite accurate activity summaries for a real world application scenario.