相关论文: GLANCE: Global to Local Architecture-Neutral Conce…

Perturbation-based explanation methods often measure the contribution of an input feature to an image classifier's outputs by heuristically removing it via e.g. blurring, adding noise, or graying out, which often produce unrealistic,…

Existing models which generate textual explanations enforce task relevance through a discriminative term loss function, but such mechanisms only weakly constrain mentioned object parts to actually be present in the image. In this paper, a…

Generative Adversarial Networks (GANs) are the driving force behind the state-of-the-art in image generation. Despite their ability to synthesize high-resolution photo-realistic images, generating content with on-demand conditioning of…

Federated Graph Learning (FGL) has emerged as a powerful paradigm for decentralized training of graph neural networks while preserving data privacy. However, existing FGL methods are predominantly designed for static graphs and rely on…

Sustainability reports are critical for ESG assessment, yet greenwashing and vague claims often undermine their reliability. Existing NLP models lack robustness to these practices, typically relying on surface-level patterns that generalize…

While deep neural networks are extremely effective at classifying images, they remain opaque and hard to interpret. We introduce local and global explanation methods for black-box models that generate explanations in terms of…

Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in…

Machine learning models have undeniably achieved impressive performance across a range of applications. However, their often perceived black-box nature, and lack of transparency in decision-making, have raised concerns about understanding…

Graph Neural Networks (GNNs) are effective for node classification in graph-structured data, but they lack explainability, especially at the global level. Current research mainly utilizes subgraphs of the input as local explanations or…

Online continual learning for image classification is crucial for models to adapt to new data while retaining knowledge of previously learned tasks. This capability is essential to address real-world challenges involving dynamic…

Ensuring the trustworthiness of graph neural networks (GNNs), which are often treated as black-box models, requires effective explanation techniques. Existing GNN explanations typically apply input perturbations to identify subgraphs that…

Despite their success in various domains, the growing dependence on GNNs raises a critical concern about the nature of the combinatorial reasoning underlying their predictions, which is often hidden within their black-box architectures.…

Despite the Graph Neural Networks' (GNNs) proficiency in analyzing graph data, achieving high-accuracy and interpretable predictions remains challenging. Existing GNN interpreters typically provide post-hoc explanations disjointed from…

Despite the substantial progress in recent years, the image captioning techniques are still far from being perfect.Sentences produced by existing methods, e.g. those based on RNNs, are often overly rigid and lacking in variability. This…

The synergy between generative and discriminative models receives growing attention. While discriminative Contrastive Language-Image Pre-Training (CLIP) excels in high-level semantics, it struggles with perceiving fine-grained visual…

Generative adversarial networks (GANs) have shown remarkable success in generation of data from natural data manifolds such as images. In several scenarios, it is desirable that generated data is well-clustered, especially when there is…

Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in…

Technological breakthroughs on smart homes, self-driving cars, health care and robotic assistants, in addition to reinforced law regulations, have critically influenced academic research on explainable machine learning. A sufficient number…

Graph neural networks (GNNs) are powerful graph-based deep-learning models that have gained significant attention and demonstrated remarkable performance in various domains, including natural language processing, drug discovery, and…

Convolutional neural networks have been widely applied to hyperspectral image classification. However, traditional convolutions can not effectively extract features for objects with irregular distributions. Recent methods attempt to address…