High-quality remote sensing imagery plays a vital role in environmental monitoring and disaster management. However, transmitting these images is challenging due to the unstable signal-to-noise ratio (SNR) and bandwidth limitations encountered in remote communications. Semantic communication, particularly deep learning-based methods, offers a promising solution by jointly optimizing source and channel coding to achieve data compression and noise resilience. Nevertheless, existing methods struggle to cope with varying channel noise and bandwidth, leading to unsatisfactory image reconstruction quality. To address these challenges, we propose a satellite-ground compression and transmission system called Adaptive Residual Joint Source-Channel Coding (ARJSCC), which is based on Deep Joint Source-Channel Coding (DeepJSCC). The ARJSCC system compresses remote sensing images into semantic information and residuals to achieve low overhead transmission and high-quality reconstruction. ARJSCC utilizes an attention module to adjust the semantic preference of the model for different SNRs, and deploys a variance-based position mask module to flexibly vary the semantic length and further compress it. These designs enable ARJSCC to automatically adapt to varying noise and bandwidth conditions. Moreover, for the residual, we apply BPG to compress it to reduce the transmission cost and design the corresponding enhancement module to recover its details from the noise-affected compressed residual. We experimentally compare our ARJSCC with the recent DeepJSCC-based wireless image transmission models in low-resolution dataset and high-resolution remote dataset under multiple wireless channel environments. The experimental results show that ARJSCC can achieve high reconstruction quality exceeding 44dB, and outperform the competitors by 4-6db even under low SNR and bandwidth environments.

Dynamic graphs are ubiquitous in our lives, yet they are also susceptible to the risks imposed by malicious activities. However, identifying anomalies in these dynamic graphs presents a challenging task due to the complex graph structures. Existing methods for dynamic anomaly detection primarily focus on learning representations for each timestamp and using sequence modeling techniques to capture and model the temporal information. Despite extensive research, dynamic anomaly detection still faces two key challenges. First, existing methods are limited in effectively using fine-grained temporal information. Second, they have limited generalization capabilities under unsupervised settings. Overcoming these challenges is crucial for advances in dynamic anomaly detection. In this paper, we propose a novel unsupervised anomaly detection method for dynamic graphs. Our approach leverages complex temporal information through fine-grained sampling and embedding modules. Additionally, we introduce an attention alignment strategy to minimize discrepancies in contextual attention between source and target nodes. Through a comprehensive evaluation, we demonstrate that our strategy effectively mitigates overfitting and improves generalization. Experiments on ten dynamic graph datasets validate the effectiveness of our proposed method in detecting anomalies.

Camouflaged Object Detection (COD) aims to segment objects that blend in with their surroundings. Most existing methods mainly tackle this issue by a single-stage framework, which tends to degrade performance in the face of small objects, low-contrast objects and objects with diverse appearances. In this paper, we propose a novel Progressive Enhancement Network (PENet) for COD by imitating the human visual detection system, which follows a three-stage detection process: locate objects, refine textures and restore boundary. Specifically, our PENet contains three key modules, i.e., the object location module (OLM), the group attention module (GAM) and the context feature restoration module (CFRM). The OLM is designed to position the object globally, the GAM is developed to refine both high-level semantic and low-level texture feature representation, and the CFRM is leveraged to effectively aggregate multi-level features for progressively restoring the clear boundary. Extensive results demonstrate that our PENet significantly outperforms 32 state-of-the-art methods on four widely used benchmark datasets

Graph self-supervised learning aims to mine useful information from unlabeled graph data, and has been successfully applied to pre-train graph representations. Many existing approaches use contrastive learning to learn powerful embeddings by learning contrastively from two augmented graph views. However, none of these graph contrastive methods fully exploits the diversity of different augmentations, and hence is prone to overfitting and limited generalization ability of learned representations. In this paper, we propose a novel Graph Self-supervised Learning method with Augmentation-aware Contrastive Learning. Our method is based on the finding that the pre-trained model after adding augmentation diversity can achieve better generalization ability. To make full use of the information from the diverse augmentation method, this paper constructs new augmentation-aware prediction task which complementary with the contrastive learning task. Similar to how pre-training requires fast adaptation to different downstream tasks, we simulate train-test adaptation on the constructed tasks for further enhancing the learning ability; this strategy can be deemed as a form of meta-learning. Experimental results show that our method outperforms previous methods and learns better representations for a variety of downstream tasks.

CRISPR/Cas9-based gene editing technology has been widely used in various cells and organisms. However, the off-target effects will bring unpredictable consequences to the organism edited. One of the main obstacles to predict CRISPR/Cas9 off-target is the imbalance of the number of positive and negative samples, which puts forward a challenge for the training of traditional deep learning algorithms. In this paper, we proposed H-VAE, a hybrid variational autoencoder model with data augmentation. This model can extract more abundant sgRNA-DNA base pair matching information, and reduce the risk of overfitting. Moreover, the sample imbalance is resolved. H-VAE can make use of underlying information of training sample, extracted by VAE, to alleviate data-imbalance problem. In view of the weak ability to extract base pair matching information of existing models, a different encoding scheme based on pair encoding is proposed, which enables the model to make full use of sgRNA-DNA base pair matching information. On the Mismatch data set, compared with DeepCRISPR, the ROC-AUC and PR-AUC increased by 0.6% and 41.9%, respectively. In the new Indels data set test scenario, compared with CRISPR-Net, the ROC-AUC and PR-AUC were increased by 1.5% and 133.4% respectively. This proves that H-VAE can improve off-target prediction in various scenarios. The improvement of PR-AUC shows that H-VAE can significantly improve the effect of unbalanced classification. The experimental results demonstrate that H-VAE could achieve a better effect compared with state-of-the-art CRISPR/Cas9 off-target methods on various types of data sets. The code and data can be obtained at https://github.com/weimingxiang/H-VAE.

CRISPR-Cas9 is causing a new revolution in many fields s uch a s b asic b iological r esearch, m edicine, a nd biotechnology as the third-generation gene-editing tool. However, the phenomenon of off-target is a stumbling block to the vigorous development of gene-editing technology. In this paper, we proposed DNA-BERT by adding more meaningful tasks that learn regulatory sequence code from genomic sequence and remove useless tasks based on original Bidirectional Encoder Representations from Transformers (BERT) model to make it more suitable for DNA sequence tasks. Due to the lack of training samples, we use it to pre-training from massive genome data and use LightGBM(Light Gradient Boosting Model) to build a classification and regression model using DNA-BERT embeddings combine with hand-crafted features including mismatches, the secondary structure and so on. The empirical results from the public benchmark demonstrate that our method achieves better performance compared with state-of-art off-target methods (i.e. Elevation, DeepCRISPR, CNN-based method, CFD, MIT, CROPIT, CCTop) on benchmark studies.

Answer selection plays a crucial role in natural language processing. and thus has received much attention. Many recent works treat it as an ad-hoc retrieval problem where ranking optimization accounts for a large proportion. Previous works mainly consider the similarity between answer and question, but rarely utilize similarity and dissimilarity relationship in the answers candidate set. In this paper, we propose a similarity aggregation method to rerank the results produced by different baseline neural networks. The key idea of similarity aggregation is that true matches should not only similar to other true matches, but also dissimilar with false matches, and inspired by multi-view verification, the true answers should have the same ranking to the question in different baseline methods and false answers are the same. The empirical results, from the public benchmark task of answer selection, demonstrate that our method has significant improvement over the baseline methods.