Specifically, we first utilize a two-phase module to generate span representations by aggregating context information based on a bottom-up and top-down transformer network.
Product-related question answering platforms nowadays are widely employed in many E-commerce sites, providing a convenient way for potential customers to address their concerns during online shopping.
The spread of rumors along with breaking events seriously hinders the truth in the era of social media.
In this paper, we study a novel problem of interpreting GNN unfairness through attributing it to the influence of training nodes.
PATE combines an ensemble of "teacher models" trained on sensitive data and transfers the knowledge to a "student" model through the noisy aggregation of teachers' votes for labeling unlabeled public data which the student model will be trained on.
Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?".
Furthermore, we analyze the privacy degradation caused by the sampling process dependent on the differentially private PageRank results during model training and propose a differentially private GNN (DPGNN) algorithm to further protect node features and achieve rigorous node-level differential privacy.
Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances.
Hypergraphs provide an effective abstraction for modeling multi-way group interactions among nodes, where each hyperedge can connect any number of nodes.
A new geometric perspective is presented to view such a problem as aligning generated distributions between the teacher and student.
Noticeably, LBSNs have offered unparalleled access to abundant heterogeneous relational information about users and POIs (including user-user social relations, such as families or colleagues; and user-POI visiting relations).
In contrast, Transformer Decoder with the causal attention masks is naturally sensitive to the word order.
Massive false rumors emerging along with breaking news or trending topics severely hinder the truth.
The diffusion of rumors on microblogs generally follows a propagation tree structure, that provides valuable clues on how an original message is transmitted and responded by users over time.
Image Captioning is a popular vision-and-language task to generate the language description of an image.
Before training the captioning models, an extra object detector is utilized to recognize the objects in the image at first.
In this framework, we generate counterfactuals corresponding to perturbations on each node's and their neighbors' sensitive attributes.
Such images form a new training set (i. e., support set) so that the incremental model is hoped to recognize a basenji (i. e., query) as a basenji next time.
Further, to mitigate the impact of MMA, a defense strategy based on multi-index information active disturbance rejection control is proposed to improve the stability and anti-disturbance ability of the power system, which considers the impact factors of both mode damping and disturbance compensation.
A common limitation of Transformer Encoder's self-attention mechanism is that it cannot automatically capture the information of word order, so one needs to feed the explicit position encodings into the target model.
Tensor factorization has been proved as an efficient unsupervised learning approach for health data analysis, especially for computational phenotyping, where the high-dimensional Electronic Health Records (EHRs) with patients' history of medical procedures, medications, diagnosis, lab tests, etc., are converted to meaningful and interpretable medical concepts.
Representation learning on static graph-structured data has shown a significant impact on many real-world applications.
The experimental results showed that the QIDNN model with 7 interactive features achieve the state-of-art accuracy $83. 25\%$.
Besides, as the confounders may be time-varying during COVID-19 (e. g., vigilance of residents changes in the course of the pandemic), it is even more difficult to capture them.
Evaluation of the risk of getting stroke is important for the prevention and treatment of stroke in China.
The development of efficient models for predicting specific properties through machine learning is of great importance for the innovation of chemistry and material science.
Ranked #3 on Drug Discovery on QM9
In this paper, we propose SkeTenSmooth, a novel tensor factorization framework that uses adaptive sampling to compress the tensor in a temporally streaming fashion and preserves the underlying global structure.
In this paper, we propose the Review-guided Answer Helpfulness Prediction (RAHP) model that not only considers the interactions between QA pairs but also investigates the opinion coherence between the answer and crowds' opinions reflected in the reviews, which is another important factor to identify helpful answers.
We propose DPFact, a privacy-preserving collaborative tensor factorization method for computational phenotyping using EHR.
Claim verification is generally a task of verifying the veracity of a given claim, which is critical to many downstream applications.
In the main Subtask C, our primary submission was ranked fourth, with a MAP of 13. 48 and accuracy of 97. 08.