Search Results for author:
Found 45 papers, 9 papers with code
Mitigating Shortcuts in Language Models with Soft Label Encoding
Recent research has shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks.
Natural Language Understanding
Out-of-Distribution Generalization
Adaptive Priority Reweighing for Generalizing Fairness Improvement
Our adaptive reweighing method prioritizes samples closer to the decision boundary and assigns a higher weight to improve the generalizability of fair classifiers.
Explainability for Large Language Models: A Survey
For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge.
A Survey on Fairness in Large Language Models
Then, for large-scale LLMs, we introduce recent fairness research, including fairness evaluation, reasons for bias, and debiasing methods.
XGBD: Explanation-Guided Graph Backdoor Detection
An emerging detection strategy in the vision and NLP domains is based on an intriguing phenomenon: when training models on a mixture of backdoor and clean samples, the loss on backdoor samples drops significantly faster than on clean samples, allowing backdoor samples to be easily detected by selecting samples with the lowest loss values.
DISPEL: Domain Generalization via Domain-Specific Liberating
Domain generalization aims to learn a generalization model that can perform well on unseen test domains by only training on limited source domains.
Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases
Meanwhile, experimental results on the GLUE benchmark show that CCPA retains the language modeling capability of PLMs.
FAIRER: Fairness as Decision Rationale Alignment
Existing fairness regularization terms fail to achieve decision rationale alignment because they only constrain last-layer outputs while ignoring intermediate neuron alignment.
DEGREE: Decomposition Based Explanation For Graph Neural Networks
Graph Neural Networks (GNNs) are gaining extensive attention for their application in graph data.
Black-box Backdoor Defense via Zero-shot Image Purification
Our proposed framework can be applied to black-box models without requiring any internal information about the poisoned model or any prior knowledge of the clean/poisoned samples.
Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions
Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input variable to the final output.
Efficient XAI Techniques: A Taxonomic Survey
Finally, we summarize the challenges of deploying XAI acceleration methods to real-world scenarios, overcoming the trade-off between faithfulness and efficiency, and the selection of different acceleration methods.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Mitigating Relational Bias on Knowledge Graphs
Knowledge graph data are prevalent in real-world applications, and knowledge graph neural networks (KGNNs) are essential techniques for knowledge graph representation learning.
Shortcut Learning of Large Language Models in Natural Language Understanding
We first introduce the concepts of shortcut learning of language models.
Mitigating Algorithmic Bias with Limited Annotations
Existing work on fairness modeling commonly assumes that sensitive attributes for all instances are fully available, which may not be true in many real-world applications due to the high cost of acquiring sensitive information.
Fair Machine Learning in Healthcare: A Review
Benefiting from the digitization of healthcare data and the development of computing power, machine learning methods are increasingly used in the healthcare domain.
Accelerating Shapley Explanation via Contributive Cooperator Selection
Even though Shapley value provides an effective explanation for a DNN model prediction, the computation relies on the enumeration of all possible input feature coalitions, which leads to the exponentially growing complexity.
Unveiling Project-Specific Bias in Neural Code Models
Neural code models have introduced significant improvements over many software analysis tasks like type inference, vulnerability detection, etc.
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding
Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks.
Was my Model Stolen? Feature Sharing for Robust and Transferable Watermarks
The main idea is to insert a watermark which is only known to defender into the protected model and the watermark will then be transferred into all stolen models.
Fairness via Representation Neutralization
This process not only requires a lot of instance-level annotations for sensitive attributes, it also does not guarantee that all fairness sensitive information has been removed from the encoder.
A General Taylor Framework for Unifying and Revisiting Attribution Methods
However, the attribution problem has not been well-defined, which lacks a unified guideline to the contribution assignment process.
Learning Disentangled Representations for Time Series
Motivated by the success of disentangled representation learning in computer vision, we study the possibility of learning semantic-rich time-series representations, which remains unexplored due to three main challenges: 1) sequential data structure introduces complex temporal correlations and makes the latent representations hard to interpret, 2) sequential models suffer from KL vanishing problem, and 3) interpretable semantic concepts for time-series often rely on multiple factors instead of individuals.
Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution
The basic idea is to learn a source signal by back-propagation such that the mutual information between input and output should be as much as possible preserved in the mutual information between input and the source signal.
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models
These two observations are further employed to formulate a measurement which can quantify the shortcut degree of each training sample.
Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation
With the wide use of deep neural networks (DNN), model interpretability has become a critical concern, since explainable decisions are preferred in high-stake scenarios.
Deep Serial Number: Computational Watermarking for DNN Intellectual Property Protection
In this paper, we present DSN (Deep Serial Number), a simple yet effective watermarking algorithm designed specifically for deep neural networks (DNNs).
A Unified Taylor Framework for Revisiting Attribution Methods
Attribution methods have been developed to understand the decision-making process of machine learning models, especially deep neural networks, by assigning importance scores to individual features.
Machine Learning Explanations to Prevent Overtrust in Fake News Detection
Combating fake news and misinformation propagation is a challenging task in the post-truth era.
An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks
In this paper, we investigate a specific security problem called trojan attack, which aims to attack deployed DNN systems relying on the hidden trigger patterns inserted by malicious hackers.
Mitigating Gender Bias in Captioning Systems
Image captioning has made substantial progress with huge supporting image collections sourced from the web.
Adversarial Attacks and Defenses: An Interpretation Perspective
In this paper, we review recent work on adversarial attacks and defenses, particularly from the perspective of machine learning interpretation.
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions.
Sub-Architecture Ensemble Pruning in Neural Architecture Search
Neural architecture search (NAS) is gaining more and more attention in recent years due to its flexibility and remarkable capability to reduce the burden of neural network design.
Distribution-Guided Local Explanation for Black-Box Classifiers
Existing local explanation methods provide an explanation for each decision of black-box classifiers, in the form of relevance scores of features according to their contributions.
Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder
The analysis further shows that LAE outperforms the state-of-the-arts by 6. 52%, 12. 03%, and 3. 08% respectively on three deepfake detection tasks in terms of generalization accuracy on previously unseen manipulations.
Fairness in Deep Learning: A Computational Perspective
Deep learning is increasingly being used in high-stake decision making applications that affect individual lives.
Learning Credible Deep Neural Networks with Rationale Regularization
Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions.
SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks
SpecAE leverages Laplacian sharpening to amplify the distances between representations of anomalies and the ones of the majority.
Deep Structured Cross-Modal Anomaly Detection
To this end, we propose a novel deep structured anomaly detection framework to identify the cross-modal anomalies embedded in the data.
Evaluating Explanation Without Ground Truth in Interpretable Machine Learning
Interpretable Machine Learning (IML) has become increasingly important in many real-world applications, such as autonomous cars and medical diagnosis, where explanations are significantly preferred to help people better understand how machine learning systems work and further enhance their trust towards systems.
BIG-bench Machine Learning
Interpretable Machine Learning
+1
XFake: Explainable Fake News Detector with Visualizations
In this demo paper, we present the XFake system, an explainable fake news detector that assists end-users to identify news credibility.
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition
REAT decomposes the final prediction of a RNN into additive contribution of each word in the input text.
Techniques for Interpretable Machine Learning
Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision.
Towards Explanation of DNN-based Prediction with Guided Feature Inversion
While deep neural networks (DNN) have become an effective computational tool, the prediction results are often criticized by the lack of interpretability, which is essential in many real-world applications such as health informatics.
