Related papers: StrAE: Autoencoding for Pre-Trained Embeddings usi…

Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional…

Neural network approaches to single-channel speech enhancement have received much recent attention. In particular, mask-based architectures have achieved significant performance improvements over conventional methods. This paper proposes a…

Building scalable models to learn from diverse, multimodal data remains an open challenge. For vision-language data, the dominant approaches are based on contrastive learning objectives that train a separate encoder for each modality. While…

Structured text understanding on Visually Rich Documents (VRDs) is a crucial part of Document Intelligence. Due to the complexity of content and layout in VRDs, structured text understanding has been a challenging task. Most existing…

We use reinforcement learning to learn tree-structured neural networks for computing representations of natural language sentences. In contrast with prior work on tree-structured models in which the trees are either provided as input or…

Developing effective representations of protein structures is essential for advancing protein science, particularly for protein generative modeling. Current approaches often grapple with the complexities of the SE(3) manifold, rely on…

Learning rich representation from data is an important task for deep generative models such as variational auto-encoder (VAE). However, by extracting high-level abstractions in the bottom-up inference process, the goal of preserving all…

Traffic forecasting, crucial for urban planning, requires accurate predictions of spatial-temporal traffic patterns across urban areas. Existing research mainly focuses on designing complex models that capture spatial-temporal dependencies…

The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such content's structure through statistical learning alone. This…

Artificial intelligence (AI) has revolutionized software engineering (SE) by enhancing software development efficiency. The advent of pre-trained models (PTMs) leveraging transfer learning has significantly advanced AI for SE. However,…

In this paper, we develop a new framework for sensing and recovering structured signals. In contrast to compressive sensing (CS) systems that employ linear measurements, sparse representations, and computationally complex convex/greedy…

Uncertainty estimation in machine learning has traditionally focused on the prediction stage, aiming to quantify confidence in model outputs while treating learned representations as deterministic and reliable by default. In this work, we…

Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the…

Deep neural networks based on layer-stacking architectures have historically suffered from poor inherent interpretability. Meanwhile, symbolic probabilistic models function with clear interpretability, but how to combine them with neural…

Stack autoencoder (SAE), as a representative deep network, has unique and excellent performance in feature learning, and has received extensive attention from researchers. However, existing deep SAEs focus on original samples without…

In this paper, we focus on the unsupervised setting for structure learning of deep neural networks and propose to adopt the efficient coding principle, rooted in information theory and developed in computational neuroscience, to guide the…

Empirical data, on which deep learning relies, has substantial internal structure, yet prevailing theories often disregard this aspect. Recent research has led to the definition of structured data ensembles, aimed at equipping established…

Recent work in learning ontologies (hierarchical and partially-ordered structures) has leveraged the intrinsic geometry of spaces of learned representations to make predictions that automatically obey complex structural constraints. We…

In this work, we propose a novel convolutional autoencoder based architecture to generate subspace specific feature representations that are best suited for classification task. The class-specific data is assumed to lie in low dimensional…

We propose a procedure for automated implicit inductive theorem proving for equational specifications made of rewrite rules with conditions and constraints. The constraints are interpreted over constructor terms (representing data values),…