Related papers: XNNTab -- Interpretable Neural Networks for Tabula…
We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate in function spaces rather than fixed-dimensional Euclidean representations. We formalize the functional representation hypothesis,…
Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption that concepts correspond to independent linear directions. However, a growing body of…
Neural networks (NNs) achieve outstanding performance in many domains; however, their decision processes are often opaque and their inference can be computationally expensive in resource-constrained environments. We recently proposed…
In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be…
Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the internal representations of large language models (LLMs), revealing latent latent features with semantical meaning. This interpretability has also…
A challenging open question in deep learning is how to handle tabular data. Unlike domains such as image and natural language processing, where deep architectures prevail, there is still no widely accepted neural architecture that dominates…
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.…
Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most…
Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…
Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models.…
Discovering patterns in data that best describe the differences between classes allows to hypothesize and reason about class-specific mechanisms. In molecular biology, for example, this bears promise of advancing the understanding of…
This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance…
Graph Neural Networks (GNNs) have become a powerful tool for modeling and analyzing data with graph structures. The wide adoption in numerous applications underscores the value of these models. However, the complexity of these methods often…
Deep neural networks (DNNs) have demonstrated impressive performance on a wide array of tasks, but they are usually considered opaque since internal structure and learned parameters are not interpretable. In this paper, we re-examine the…
In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional…
While deep learning has achieved remarkable success across many domains, it has historically underperformed on tabular learning tasks, which remain dominated by gradient boosting decision trees. However, recent advancements are paving the…
Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility to understand and interpret the network…
RFdiffusion is a popular and well-established model for generation of protein structures. However, this generative process offers limited insight into its internal representations and how they contribute to the final protein structure.…
Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…
Tabular data is the foundation of the information age and has been extensively studied. Recent studies show that neural-based models are effective in learning contextual representation for tabular data. The learning of an effective…