相关论文: Symbolic Autoencoding for Self-Supervised Sequence…

Generative models of graphs are well-known, but many existing models are limited in scalability and expressivity. We present a novel sequential graphical variational autoencoder operating directly on graphical representations of data. In…

Although semi-supervised variational autoencoder (SemiVAE) works in image classification task, it fails in text classification task if using vanilla LSTM as its decoder. From a perspective of reinforcement learning, it is verified that the…

Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks, e.g., dimensionality reduction, image compression, and image denoising. An AE has two goals: (i) compress the original input to a…

Self-supervised learning (SSL) has become a popular method for generating invariant representations without the need for human annotations. Nonetheless, the desired invariant representation is achieved by utilising prior online…

Symbolic regression (SR) -- which learns symbolic equations to describe the underlying relation from input-output pairs -- is widely used for scientific discovery. However, a rich set of scientific data from the real world (e.g., particle…

The choice of an appropriate bottleneck dimension and the application of effective regularization are both essential for Autoencoders to learn meaningful representations from unlabeled data. In this paper, we introduce a new class of…

Transformer-based large language models exhibit groundbreaking capabilities, but their storage and computational costs are prohibitively high, limiting their application in resource-constrained scenarios. An effective approach is to…

We propose an approach to symbolic regression based on a novel variational autoencoder for generating hierarchical structures, HVAE. It combines simple atomic units with shared weights to recursively encode and decode the individual nodes…

Recent work shows that Sparse Autoencoders (SAE) applied to large language model (LLM) layers have neurons corresponding to interpretable concepts. These SAE neurons can be modified to align generated outputs, but only towards…

Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisation capabilities of Transformer-based auto-regressive language…

In recent years, deep neural networks have yielded state-of-the-art performance on several tasks. Although some recent works have focused on combining deep learning with recommendation, we highlight three issues of existing models. First,…

Learning aligned multimodal embeddings from weakly paired, label-free corpora is challenging: pipelines often provide only pre-extracted features, clips contain multiple events, and spurious co-occurrences. We propose HSC-MAE (Hierarchical…

By composing graphical models with deep learning architectures, we learn generative models with the strengths of both frameworks. The structured variational autoencoder (SVAE) inherits structure and interpretability from graphical models,…

Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node. Many of the existing methods focus on obtaining a static vector…

The recent emergence of Self-Supervised Learning (SSL) as a fundamental paradigm for learning image representations has, and continues to, demonstrate high empirical success in a variety of tasks. However, most SSL approaches fail to learn…

Masked Autoencoding (MAE) has emerged as an effective approach for pre-training representations across multiple domains. In contrast to discrete tokens in natural languages, the input for image MAE is continuous and subject to additional…

Autoencoding, which aims to reconstruct the input images through a bottleneck latent representation, is one of the classic feature representation learning strategies. It has been shown effective as an auxiliary task for semi-supervised…

Sparse autoencoders (SAEs) have emerged as powerful techniques for interpretability of large language models (LLMs), aiming to decompose hidden states into meaningful semantic features. While several SAE variants have been proposed, there…

While diffusion models excel at image synthesis, useful representations have been shown to emerge from generative pre-training, suggesting a path towards unified generative and discriminative learning. However, suboptimal semantic flow…

Sparse autoencoders (SAEs) have proven effective for extracting monosemantic features from large language models (LLMs), yet these features are typically identified in isolation. However, broad evidence suggests that LLMs capture the…