Given the limited number of labeled magnetotelluric (MT) filed data samples, current neural network (NN) inversions for MT are primarily rely on synthetic data, which may not fully capture the complexity of true underground resistivity structures. This letter introduces a novel inversion scheme that combines attention U-Net with transfer learning (AUTL) to bridge this gap. The proposed method improves inversion accuracy by integrating field data into the training process through transfer learning (TL), using 3-D models derived from real field measurements as the target dataset. This enhances the authenticity and reliability of the inversion results. Additionally, the incorporation of attention gates (AGs) significantly improves feature extraction by focusing on relevant features. We validate the effectiveness of the AUTL approach using both synthetic and measured data, demonstrating its superior performance in reconstructing underground resistivity structures with high accuracy and noise resistance. This method offers a promising solution for training inversion networks with limited field MT data and lays the groundwork for expanding datasets with more diverse 3-D models in the future.

Duration bias widely exists in video recommendations, where models tend to recommend short videos for the higher ratio of finish playing and thus possibly fail to capture users' true interests. In this paper, we eliminate the duration bias from both data and model. First, based on the extensive data analysis, we observe that play completion rate of videos with the same duration presents a bimodal distribution. Hence, we propose to perform threshold division to construct binary labels as training labels for alleviating the drawback of finish playing labels overly biased towards short videos. Algorithmically, we resort to causal inference, which enables us to inspect causal relationships of video recommendations with a causal graph. We identify that duration has two kinds of effect on prediction: direct and indirect. Duration bias lies in the direct effect, while the indirect effect benefits prediction. To this end, we design a model-agnostic Counterfactual Video Recommendation for Duration Debiasing (CVRDD) framework, which incorporates multi-task learning to estimate different causal effect during training. In the inference phase, we perform counterfactual inference to remove the direct effect of duration for unbiased prediction. We conduct experiments on two industrial datasets, and in addition to achieving highly promising results on traditional top-k recommendation metrics, CVRDD also improves the user watch time.

Predicting the popularity of online videos has many real-world applications, such as recommendation, precise advertising, and edge caching strategies. Despite many efforts have been dedicated to the online video popularity prediction, there still exist several challenges: (1) The meta-data from online videos is usually sparse and noisy, which makes it difficult to learn a stable and robust representation. (2) The influence of content features and temporal features in different life cycles of online videos is dynamically changing, so it is necessary to build a model that can capture the dynamics. (3) Besides, there is a great need to interpret the predictive behavior of the model to assist administrators of video platforms in the subsequent decision-making.