no code implementations • • Jiangang Bai, Yujing Wang, Hong Sun, Ruonan Wu, Tianmeng Yang, Pengfei Tang, Defu Cao, Mingliang Zhang1, Yunhai Tong, Yaming Yang, Jing Bai, Ruofei Zhang, Hao Sun, Wei Shen
Large-scale pre-trained language models have attracted extensive attentions in the research community and shown promising results on various tasks of natural language processing.
Despite their success, the existing PETL methods in CV can be computationally expensive and require large amounts of memory and time cost during training, which limits low-resource users from conducting research and applications on large models.
To address these issues, we propose a Time-aware Graph Structure Learning (TGSL) approach via sequence prediction on temporal graphs, which learns better graph structures for downstream tasks through adding potential temporal edges.
We have also provided a theoretical justification for delta tuning can improve the generalization ability of GNNs by applying generalization bounds.
Nowadays, HSI classification can reach a high classification accuracy when given sufficient labeled samples as training set.
Our framework is based on an innovative evolution algorithm, which is stable and suitable for multiple dataset scenario.
Specifically, we creatively propose Multi-granularity Intent Heterogeneous Session Graph which captures the interactions between different granularity intent units and relieves the burden of long-dependency.
Creating labeled training sets has become one of the major roadblocks in machine learning.
On the one hand, multi-hop-based approaches do not explicitly distinguish relevant nodes from a large number of multi-hop neighborhoods, leading to a severe over-smoothing problem.
However, simply integrating KGs in current KG-based RS models is not necessarily a guarantee to improve the recommendation performance, which may even weaken the holistic model capability.
We design an adaptive auxiliary loss weighting model to learn the weights of auxiliary tasks by quantifying the consistency between auxiliary tasks and the target task.
In this paper, we propose Spectral Temporal Graph Neural Network (StemGNN) to further improve the accuracy of multivariate time-series forecasting.
Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information.
In this paper, we propose a novel and generic mechanism based on evolving attention to improve the performance of transformers.
Instead, we model their dependencies via a chain of prediction models that take previous attention maps as input to predict the attention maps of a new layer through convolutional neural networks.
We add the model designed by AutoADR as a sub-model into the production Ad Relevance model.
Anomaly detection on multivariate time-series is of great importance in both data mining research and industrial applications.
BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks.
Learning text representation is crucial for text classification and other language related tasks.
For these applications, graph embedding is crucial as it provides vector representations of the graph.