Recent research has shown that large language models rely on spurious
co...
With the increasing penetration of machine learning applications in crit...
Large language models (LLMs) have demonstrated impressive capabilities i...
Large language models (LLMs) have shown powerful performance and develop...
Backdoor attacks pose a significant security risk to graph learning mode...
Domain generalization aims to learn a generalization model that can perf...
As the representation capability of Pre-trained Language Models (PLMs)
i...
Graph Neural Networks (GNNs) are gaining extensive attention for their
a...
Backdoor attacks inject poisoned data into the training set, resulting i...
Various attribution methods have been developed to explain deep neural
n...
Recently, there has been a growing demand for the deployment of Explaina...
Large language models (LLMs) have achieved state-of-the-art performance ...
Existing work on fairness modeling commonly assumes that sensitive attri...
Benefiting from the digitization of healthcare data and the development ...
Even though Shapley value provides an effective explanation for a DNN mo...
Recent works have focused on compressing pre-trained language models (PL...
Existing bias mitigation methods for DNN models primarily work on learni...
Attribution methods provide an insight into the decision-making process ...
Time-series representation learning is a fundamental task for time-serie...
Back propagation based visualizations have been proposed to interpret de...
Recent studies indicate that NLU models are prone to rely on shortcut
fe...
With the wide use of deep neural networks (DNN), model interpretability ...
In this paper, we introduce DSN (Deep Serial Number), a new watermarking...
Attribution methods have been developed to understand the decision makin...
Combating fake news and misinformation propagation is a challenging task...
Image captioning has made substantial progress with huge supporting imag...
With the widespread use of deep neural networks (DNNs) in high-stake
app...
Recent years have witnessed the significant advances of machine learning...
Recently, more and more attention has been drawn into the internal mecha...
Neural architecture search (NAS) is gaining more and more attention in r...
With advancements of deep learning techniques, it is now possible to gen...
Deep learning is increasingly being used in high-stake decision making
a...
Recent explainability related studies have shown that state-of-the-art D...
Anomaly detection aims to distinguish observations that are rare and
dif...
Anomaly detection is a fundamental problem in data mining field with man...
Interpretable Machine Learning (IML) has become increasingly important i...
In this demo paper, we present the XFake system, an explainable fake new...
RNN models have achieved the state-of-the-art performance in a wide rang...
Interpretable machine learning tackles the important problem that humans...
While deep neural networks (DNN) have become an effective computational ...