Semi-supervised medical image segmentation (SSMIS) mainly leverages valuable information from unlabeled data to complement the limited labeled guidance. Incorporating SAM, with its excellent generalization capabilities, enhances the learning process from unlabeled data, as demonstrated by existing methods. However, most current SAM-based methods in SSMIS focus on unique prompt design, while the prompts generated for unlabeled data through pseudo-labels unavoidably introduce noise, limiting the following decoding process. In this paper, we propose a Cross-Hierarchical Decoding (CHD) process for SAM, which removes explicit prompts (e.g., point or box) and thus mitigates the influence of inaccurate pseudo labels. Specifically, our CHD is a two-stage decoder. The first stage uses the original decoder in SAM to generate probability masks, which are combined with a learnable mask interaction module in the second stage to achieve more fine-grained segmentation. Meanwhile, to remove the restriction that the original SAM can only segment foreground-background categories, we design a cross-class correlation module in CHD to capture class-wise interrelationships between different classes, thus achieving multi-class segmentation. Extensive experiments show that CHD achieves new state-of-the-art performance for SSMIS, significantly improving different baselines.

Recommender systems in various applications often encounter the challenge of cold-start, which refers to how to provide recommendations for completely new users. Cross-domain recommendation offers a solution to address this cold-start issue by leveraging user interaction information from other domains and providing recommendations for users in the target domain. However, applying the classic two-tower model in cross-domain scenarios for pure cold-start users proves challenging, and most existing cross-domain cold-start recommendation models adopt an embedding-mapping framework that lacks end-to-end efficiency. The parallel training recommendation method lacks consideration of the domain-level intrinsic characteristics of cross-domain information. In this paper, we propose a generalized framework that Domain-level Disentanglement framework based on information enhancement for Cross-domain Cold-start Recommendation. On one hand, we achieve deep utilization of domain-level information through independent extraction of domain knowledge and fusion using heuristic strategies. On the other hand, our model is incorporated with an information enhancement network based on user attention and a user personalized adaptor. We introduce measures to assess user variability and immutability in cross-domain recommendation, aiming to eliminate inter-domain bias and highlight individual user preferences. Experimental results on widely used cross-domain recommendation datasets demonstrate that our proposed model outperforms state-of-the-art methods, validating its effectiveness.

Social recommendation leverages the social connections between users to mitigate the issue of data sparsity and enhance recommendation quality. Although existing related works show their effectiveness, there remain two critical questions: i) The patterns of preference interactions among users are varied and heterogeneous. Current models struggle to accurately capture preference shifts from user interactions in noisy social environments. ii) Existing methods handle the integration of auxiliary information coarsely, potentially introducing noise and leading to biases in user preferences. To address the limitations above, we introduce a novel framework named Robust Graph Based Social Recommendation through Contrastive Multi-view Learning (RGCML). This framework leverages denoised social relations and global intents as dual auxiliary information sources to provide comprehensive characterization of users. Firstly, RGCML employs the concept of opinion dynamics to simulate how user preferences evolve due to noisy social relations. Then, it utilizes a specifically designed information fusion module to extract critical contextual information from multiple semantic perspectives, thereby achieving efficient personalized information fusion. Finally, it adopts the designed global-local contrastive learning paradigm that untangles and discriminates user preferences from global intents, further addressing the noise problem and enhancing the quality of user representations. Extensive experiments conducted on three real-world datasets demonstrate the superior performance of RGCML compared to several state-of-the-art (SOTA) baselines.

Social Networking Services (SNS) are one of the most widely used web applications and have a profound influence on the real world. Network structure analysis plays a crucial role in the optimization of the functionalities of SNS. In particular, subgraph statistics is widely used as a fundamental method to reveal the basic features and patterns of networks. However, one of the main challenges in data collection is how to perform effective analysis without violating users’ privacy. Existing privacy-preserving subgraph statistics methods mainly rely on enumeration, which are often inefficient or require multiple rounds of interactions. It is difficult to meet the needs of rapidly evolving social network services. To address this problem, we propose a set of new algorithms that aim to improve the efficiency and accuracy of subgraph counting under privacy preservation. By focusing on two typical network structures, the Random network and Barabási-Albert network, our approach is able to efficiently analyse the network structure while ensuring individual privacy. These algorithms perform with high accuracy in experiments, especially in evaluating triangles in BA networks, when compared with the state-of-the-art algorithm.