In recent years, deep neural networks have achieved great success in many fields, such as computer vision and natural language processing. Traditional image recommendation algorithms use text‐based recommendation methods. The process of displaying images requires a lot of time and labor, and the time‐consuming labor is inefficient. Therefore, this article mainly studies image recommendation algorithms based on deep neural networks in social networks. First, according to the time stamp information of the dataset, the interaction records of each user are sorted by the closest time. Then, some feature vectors are created via traditional feature algorithms like LBP, BGC3, RTU, or CNN extraction. For image recommendation, two LSTM neural networks are established, which accept these feature vectors as input, respectively. The compressed output of the two sub‐ESTM neural networks is used as the input of another LSTM neural network. The multilayer regression algorithm is adopted to randomly sample some network nodes to obtain the cognitive information of the nodes sampled in the entire network, predict the relationship between all nodes in the network based on the cognitive information, and perform low sampling to achieve relationship prediction. The experiments show that proposed LSTM model together with CNN feature vectors can outperform other algorithms.

In this paper, we present UniADS, the first Universal Architecture-Distiller Search framework for co-optimizing student architecture and distillation policies. Teacher-student distillation gap limits the distillation gains. Previous approaches seek to discover the ideal student architecture while ignoring distillation settings. In UniADS, we construct a comprehensive search space encompassing an architectural search for student models, knowledge transformations in distillation strategies, distance functions, loss weights, and other vital settings. To efficiently explore the search space, we utilize the NSGA-II genetic algorithm for better crossover and mutation configurations and employ the Successive Halving algorithm for search space pruning, resulting in improved search efficiency and promising results. Extensive experiments are performed on different teacher-student pairs using CIFAR-100 and ImageNet datasets. The experimental results consistently demonstrate the superiority of our method over existing approaches. Furthermore, we provide a detailed analysis of the search results, examining the impact of each variable and extracting valuable insights and practical guidance for distillation design and implementation.

Generative adversarial networks as a powerful technique is also used in domain adaptation (DA) problem. Existing adversarial DA methods mainly conduct domain-wise alignment to alleviate marginal distribution shift between the two domains, while it may damage latent discriminative structure hidden in data feature space and cause negative transfer accordingly. To handle this problem, we propose a joint adversarial domain adaptation method with structural graph alignment to minimize joint distribution bias by further realizing class-wise matching (conditional distribution shift) based on a simple sampling strategy except for the domain-wise alignment, and validate that simultaneously considering these two types of shift can approximately reduce the joint distribution bias. To explore transferable structural information and realize more sufficient transfer for DA problem, we propose to align structural graphs between the two domains which is also based on a simple sampling strategy. Notably, the structural graph describes the relationship between each two samples and it is computed on two domains. As such, we can learn new feature representation of the two domains which are more discriminative and transferable to benefit a cross-domain classification task desirably. Finally, we design a number of experiments to evaluate our approach on four public cross-domain benchmark datasets including standard and large-scale ones, and empirical results show that the proposed model can outperform compared state-of-the-art methods.

The task of domain generalization is to learn a classification model from multiple source domains and generalize it to unknown target domains. The key to domain generalization is learning discriminative domain-invariant features. Invariant representations are achieved using adversarial domain generalization as one of the primary techniques. For example, generative adversarial networks have been widely used, but suffer from the problem of low intra-class diversity, which can lead to poor generalization ability. To address this issue, we propose a new method called auxiliary classifier in adversarial domain generalization (CloCls). CloCls improve the diversity of the source domain by introducing auxiliary classifier. Combining typical task-related losses, e.g., cross-entropy loss for classification and adversarial loss for domain discrimination, our overall goal is to guarantee the learning of condition-invariant features for all source domains while increasing the diversity of source domains. Further, inspired by smoothing optima have improved generalization for supervised learning tasks like classification. We leverage that converging to a smooth minima with respect task loss stabilizes the adversarial training leading to better performance on unseen target domain which can effectively enhances the performance of domain adversarial methods. We have conducted extensive image classification experiments on benchmark datasets in domain generalization, and our model exhibits sufficient generalization ability and outperforms state-of-the-art DG methods.

Emotional tracking on time-varying virtual space communication aims to identify sentiments and opinions expressed in a piece of user-generated content. However, the existing research mainly focuses on the user’s single post, despite the fact that social network data are sequential. In this article, we propose a sentiment analysis model based on time series prediction in order to understand and master the chronological evolution of the user’s point of view. Specifically, with the help of a domain-knowledge-enhanced pre-trained encoder, the model embeds tokens for each moment in the text sequence. We then propose an attention-based temporal prediction model to extract rich timing information from historical posting records, which improves the prediction of the user’s current state and personalizes the analysis of user’s sentiment changes in social networks. The experiments show that the proposed model improves on four kinds of sentiment tasks and significantly outperforms the strong baseline.

This is a task of computational chemistry and pharmaceutical development, with rapidly growing relevance for consumer healthcare electronics: deducing three-dimensional molecular structures from two-dimensional diagrams. In this paper, we introduce a new generative model, DOGMH, specifically tailored for applications on consumer electronic devices, which considerably increases the accuracy in this process. DOGMH borrows from the diffusion mechanisms of classical nonequilibrium thermodynamics and treats atoms as individual particles, excelling in the inversion of the diffusion process-turning noise into organized molecular structures. Our approach leverages a specially tailored bilevel optimization technique that ensures roto-translational invariance and allows for efficient processing on resource-constrained consumer devices. We show that DOGMH outperforms existing methods in terms of both conformational synthesis and distance distribution accuracy. DOGMH also provides the ability to create AI-enabled interactive 3D visualizations of molecular structures for consumer health education. Our work paves the way for advanced molecular informatics capabilities in consumer-grade devices and will potentially revolutionize personal healthcare management through AI-enhanced insights. By bridging the gap between complex molecular modeling and consumer electronics, DOGMH will open up a new frontier in intelligent, molecularly aware health devices accessible to the general public.