Graph neural networks (GNNs) have seen widespread usage across multiple real-world applications, yet in transductive learning, they still face challenges in accuracy, efficiency, and scalability, due ...to the extensive number of trainable parameters in the embedding table and the paradigm of stacking neighborhood aggregations. This paper presents a novel model called xGCN for large-scale network embedding, which is a practical solution for link predictions. xGCN addresses these issues by encoding graph-structure data in an extreme convolutional manner, and has the potential to push the performance of network embedding-based link predictions to a new record. Specifically, instead of assigning each node with a directly learnable embedding vector, xGCN regards node embeddings as static features. It uses a propagation operation to smooth node embeddings and relies on a Refinement neural Network (RefNet) to transform the coarse embeddings derived from the unsupervised propagation into new ones that optimize a training objective. The output of RefNet, which are well-refined embeddings, will replace the original node embeddings. This process is repeated iteratively until the model converges to a satisfying status. Experiments on three social network datasets with link prediction tasks show that xGCN not only achieves the best accuracy compared with a series of competitive baselines but also is highly efficient and scalable.
We present RLLTE: a long-term evolution, extremely modular, and open-source framework for reinforcement learning (RL) research and application. Beyond delivering top-notch algorithm implementations, ...RLLTE also serves as a toolkit for developing algorithms. More specifically, RLLTE decouples the RL algorithms completely from the exploitation-exploration perspective, providing a large number of components to accelerate algorithm development and evolution. In particular, RLLTE is the first RL framework to build a complete and luxuriant ecosystem, which includes model training, evaluation, deployment, benchmark hub, and large language model (LLM)-empowered copilot. RLLTE is expected to set standards for RL engineering practice and be highly stimulative for industry and academia.
With the dramatic growth of hate speech on social media during the COVID-19 pandemic, there is an urgent need to detect various hate speech effectively. Existing methods only achieve high performance ...when the training and testing data come from the same data distribution. The models trained on the traditional hateful dataset cannot fit well on COVID-19 related dataset. Meanwhile, manually annotating the hate speech dataset for supervised learning is time-consuming. Here, we propose COVID-HateBERT, a pre-trained language model to detect hate speech on English Tweets to address this problem. We collect 200M English tweets based on COVID-19 related hateful keywords and hashtags. Then, we use a classifier to extract the 1.27M potential hateful tweets to re-train BERT-base. We evaluate our COVID-HateBERT on four benchmark datasets. The COVID-HateBERT achieves a 14.8%-23.8% higher macro average F1 score on traditional hate speech detection comparing to baseline methods and a 2.6%-6.73% higher macro average F1 score on COVID-19 related hate speech detection comparing to classifiers using BERT and BERTweet, which shows that COVID-HateBERT can generalize well on different datasets.
During the global COVID-19 pandemic, people utilized social media platforms, especially Twitter, to spread and express opinions about the pandemic. Such discussions also drove the rise in ...COVID-related offensive speech. In this work, focusing on Twitter, we present a comprehensive analysis of COVID-related offensive tweets and their targets. We collected a COVID-19 dataset with over 747 million tweets for 30 months and fine-tuned a BERT classifier to detect offensive tweets. Our offensive tweets analysis shows that the ebb and flow of COVID-related offensive tweets potentially reflect events in the physical world. We then studied the targets of these offensive tweets. There was a large number of offensive tweets with abusive words, which could negatively affect the targeted groups or individuals. We also conducted a user network analysis, and found that offensive users interact more with other offensive users and that the pandemic had a lasting impact on some offensive users. Our study offers novel insights into the persistence and evolution of COVID-related offensive tweets during the pandemic
Pre-trained multilingual language models play an important role in cross-lingual natural language understanding tasks. However, existing methods did not focus on learning the semantic structure of ...representation, and thus could not optimize their performance. In this paper, we propose Multi-level Multilingual Knowledge Distillation (MMKD), a novel method for improving multilingual language models. Specifically, we employ a teacher-student framework to adopt rich semantic representation knowledge in English BERT. We propose token-, word-, sentence-, and structure-level alignment objectives to encourage multiple levels of consistency between source-target pairs and correlation similarity between teacher and student models. We conduct experiments on cross-lingual evaluation benchmarks including XNLI, PAWS-X, and XQuAD. Experimental results show that MMKD outperforms other baseline models of similar size on XNLI and XQuAD and obtains comparable performance on PAWS-X. Especially, MMKD obtains significant performance gains on low-resource languages.
In this paper we reported the fabrication of the ultra-thin freestanding diamond windows for soft X-ray optics using hot filament CVD method. The diamond film of the window is totally freestanding in ...a central aperture of 4–8 mm. Raman spectra, XRD and SEM show the deposited diamond films in our laboratory are high quality polycrystalline diamond films. The absolute transmissions of the diamond windows of 0.4–1.0 μm thickness were measured in the energy range between 75 and 1600 eV. For a freestanding diamond window of 0.4 μm thickness the absolute transmission of carbon fluorescence (
E=284 eV) is as high as 0.59. It will have a variety of applications as an X-ray window for submicron lithography of integrated circuits and X-ray spectroscopy, particularly, for characteristic soft X-ray detection of light elements.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Pixel-level Video Understanding in the Wild Challenge (PVUW) focus on complex video understanding. In this CVPR 2024 workshop, we add two new tracks, Complex Video Object Segmentation Track based on ...MOSE dataset and Motion Expression guided Video Segmentation track based on MeViS dataset. In the two new tracks, we provide additional videos and annotations that feature challenging elements, such as the disappearance and reappearance of objects, inconspicuous small objects, heavy occlusions, and crowded environments in MOSE. Moreover, we provide a new motion expression guided video segmentation dataset MeViS to study the natural language-guided video understanding in complex environments. These new videos, sentences, and annotations enable us to foster the development of a more comprehensive and robust pixel-level understanding of video scenes in complex environments and realistic scenarios. The MOSE challenge had 140 registered teams in total, 65 teams participated the validation phase and 12 teams made valid submissions in the final challenge phase. The MeViS challenge had 225 registered teams in total, 50 teams participated the validation phase and 5 teams made valid submissions in the final challenge phase.
This work deals with the variation of urinary metabolite of patients suffering from premenstrual syndrome (PMS) and the function of
Jingqianping granules (JG) in intervening liver-Qi invasion by ...metabonomic. The metabonomic characteristics and the micromolecular marking compound, which are closely related to the pathogenesis of PMS liver-Qi invasion cases, are also investigated. PMS liver-Qi invasion cases are calibrated according to the diagnostic criteria, including criteria, and excluding criteria. The urine samples from PMS liver-Qi invasion patients are analyzed at different times using UPLC-Q-TOF in combination with PCA pattern analysis, followed by discrimination of the metabolic outline and searching for the possible biological tags and metabolic pathways. The metabolic outline of premenstrual urine samples has significant difference among the control group, the PMS liver-Qi invasion group, and the PMS liver-Qi invasion treatment group. The metabolic outline of premenstrual urine sample of the PMS liver-Qi invasion group diverges from the premenstrual and postmenstrual urine samples of the control group and the postmenstrual urine sample of the PMS liver-Qi invasion group. Compared with the control group, N-acetyl-2-glutamate-5-semialdehyde has decreased greatly in the N-acetyl-2-glutamate-5-semialdehyde liver-Qi invasion group, and histidine and 3-methoxy-4-hydroxymandelaldehyde have increased significantly. This research, for the first time, deals with the metabolic pattern differences between the control group and the administration group. It shows that JG may repair metabolic disturbance of endogenous micromolecules in PMS liver-Qi invasion cases in terms of metabonomics. It also demonstrates that symptoms present before menstruation in PMS patients and the characteristic of PMS is that the symptoms appear before menstruation and disappear after it among PMS liver-Qi invasion cases.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK