Recent advancements in Pre-trained Language Models (PLMs) have significantly enhanced performance across various Natural Language Processing (NLP) tasks. However, the variability in data distributions across different domains presents challenges in generalizing these models to unseen domains. Domain generalization offers a promising solution, but existing text domain generalization methods typically rely on adversarial training to learn domain-invariant features, which often leads to models with high computational and memory overhead. To address this issue, this paper proposes a novel solution named Generalization via Prompts and Contrastive Learning (GenPromptCL) to enhance the generalization capability in domain generalization. GenPromptCL consists of two key components: Domain-Misleading Prompt Learning (DMPL) and Pseudo Label-based Contrastive Learning (PCL). Specifically, DMPL disrupts domain labels randomly, misleading the model into producing incorrect domain labels. This forces the model to learn domain-invariant features. Meanwhile, PCL generates pseudo labels within a single mini-batch, enabling the model to learn both intra-class and inter-class discriminative representations with low time and space complexity. Extensive experimental results demonstrate that GenPromptCL achieves state-of-the-art performance on three distinct text classification tasks (sentiment analysis, rumor detection, and natural language inference) while significantly improving model operation efficiency.

Trustworthy multi-view learning has attracted extensive attention because evidence learning can provide reliable uncertainty estimation to enhance the credibility of multi-view predictions. Existing trusted multi-view learning methods implicitly assume that multi-view data is secure. However, in safety-sensitive applications such as autonomous driving and security monitoring, multi-view data often faces threats from adversarial perturbations, thereby deceiving or disrupting multi-view models. This inevitably leads to the adversarial unreliability problem (AUP) in trusted multi-view learning. To overcome this tricky problem, we propose a novel multi-view learning framework, namely Reliable Disentanglement Multi-view Learning (RDML). Specifically, we first propose evidential disentanglement learning to decompose each view into clean and adversarial parts under the guidance of corresponding evidences, which is extracted by a pretrained evidence extractor. Then, we employ the feature recalibration module to mitigate the negative impact of adversarial perturbations and extract potential informative features from them. Finally, to further ignore the irreparable adversarial interferences, a view-level evidential attention mechanism is designed. Extensive experiments on multi-view classification tasks with adversarial attacks show that RDML outperforms the state-of-the-art methods by a relatively large margin. Our code is available at https://github.com/Willy1005/2025-IJCAI-RDML.

Emojis in texts provide lots of additional information in sentiment analysis. Previous implicit sentiment analysis models have primarily treated emojis as unique tokens or deleted them directly, and thus have ignored the explicit sentiment information inside emojis. Considering the different relationships between emoji descriptions and texts, we propose a pre-training Bidirectional Encoder Representations from Transformers (BERT) with emojis (BEMOJI) for Chinese and English sentiment analysis. At the pre-training stage, we pre-train BEMOJI by predicting the emoji descriptions from the corresponding texts via prompt learning. At the fine-tuning stage, we propose a fusion layer to fuse text representations and emoji descriptions into fused representations. These representations are used to predict text sentiment orientations. Experimental results show that BEMOJI gets the highest accuracy (91.41% and 93.36%), Macro-precision (91.30% and 92.85%), Macro-recall (90.66% and 93.65%) and Macro-F1-measure (90.95% and 93.15%) on the Chinese and English datasets. The performance of BEMOJI is 29.92% and 24.60% higher than emoji-based methods on average on Chinese and English datasets, respectively. Meanwhile, the performance of BEMOJI is 3.76% and 5.81% higher than transformer-based methods on average on Chinese and English datasets, respectively. The ablation study verifies that the emoji descriptions and fusion layer play a crucial role in BEMOJI. Besides, the robustness study illustrates that BEMOJI achieves comparable results with BERT on four sentiment analysis tasks without emojis, which means BEMOJI is a very robust model. Finally, the case study shows that BEMOJI can output more reasonable emojis than BERT.

MOTIVATION: The confusion of acute inflammation infected by virus and bacteria or noninfectious inflammation will lead to missing the best therapy occasion resulting in poor prognoses. The diagnostic model based on host gene expression has been widely used to diagnose acute infections, but the clinical usage was hindered by the capability across different samples and cohorts due to the small sample size for signature training and discovery. RESULTS: Here, we construct a large-scale dataset integrating multiple host transcriptomic data and analyze it using a sophisticated strategy which removes batch effect and extracts the common information from different cohorts based on the relative expression alteration of gene pairs. We assemble 2680 samples across 16 cohorts and separately build gene pair signature (GPS) for bacterial, viral, and noninfected patients. The three GPSs are further assembled into an antibiotic decision model (bacterial-viral-noninfected GPS, bvnGPS) using multiclass neural networks, which is able to determine whether a patient is bacterial infected, viral infected, or noninfected. bvnGPS can distinguish bacterial infection with area under the receiver operating characteristic curve (AUC) of 0.953 (95% confidence interval, 0.948-0.958) and viral infection with AUC of 0.956 (0.951-0.961) in the test set (N = 760). In the validation set (N = 147), bvnGPS also shows strong performance by attaining an AUC of 0.988 (0.978-0.998) on bacterial-versus-other and an AUC of 0.994 (0.984-1.000) on viral-versus-other. bvnGPS has the potential to be used in clinical practice and the proposed procedure provides insight into data integration, feature selection and multiclass classification for host transcriptomics data. AVAILABILITY AND IMPLEMENTATION: The codes implementing bvnGPS are available at https://github.com/Ritchiegit/bvnGPS. The construction of iPAGE algorithm and the training of neural network was conducted on Python 3.7 with Scikit-learn 0.24.1 and PyTorch 1.7. The visualization of the results was implemented on R 4.2, Python 3.7, and Matplotlib 3.3.4.

Misinformation has brought great challenges to the government and network media in social networks. To clarify the influences of behaviors of the network media, government, and netizen on misinformation propagation, a large number of influence parameters are proposed for the three participants. Then, a tripartite evolutionary game model for misinformation propagation is constructed. According to the proposed game model, the expected payoffs of three participants are analyzed when they adopt different strategies. The evolutionary stabilities of the game model are also analyzed theoretically. Finally, the impacts of different parameters on expected payoffs of three participants are analyzed experimentally. Meanwhile, coping strategies of three participants under different conditions are given. The experimental results show that the proposed tripartite evolutionary game model can properly describe the influence of network media, government, and netizen on misinformation propagation.

Online influence maximization (OIM) is a popular problem in social networks to learn influence propagation model parameters and maximize the influence spread at the same time. Most previous studies focus on the independent cascade (IC) model under the edge-level feedback. In this paper, we address OIM in the linear threshold (LT) model. Because node activations in the LT model are due to the aggregated effect of all active neighbors, it is more natural to model OIM with the nodel-level feedback. And this brings new challenge in online learning since we only observe aggregated effect from groups of nodes and the groups are also random. Based on the linear structure in node activations, we incorporate ideas from linear bandits and design an algorithm $\ltlinucb$ that is consistent with the observed feedback. By proving group observation modulated (GOM) bounded smoothness property, a novel result of the influence difference in terms of the random observations, we provide a regret of order $\tilde{O}(\mathrm{poly}(m)\sqrt{T})$, where $m$ is the number of edges and $T$ is the number of rounds. This is the first theoretical result in such order for OIM under the LT model. In the end, we also provide an algorithm $\oimetc$ with regret bound $O(\mathrm{poly}(m)\ T^{2/3})$, which is model-independent, simple and has less requirement on online feedback and offline computation.