arXiv research

Paper uses deep learning to model systems with degrading behavior.

PROTOCOL tackles imbalanced multi-view clustering by enhancing contrastive learning.

Sparse Transformers degrade semantic information first, with early layers encoding more.

PARIS reduces imbalanced regression datasets by pruning uninformative samples.

Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations. The recent pruning based work ESE suffers from degradation of performance/energy efficiency due to the irregular network structure after pruning. We propose bl…

Contrastive learning performance doesn't degrade with more negative samples.

Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning on reading comprehension tasks with a language representation model pre-trained on multi-lingual corp…

Improves performance of deep GCNs by controlling node feature variance.

Measures DNA quality degradation effects.

Modeling coating degradation with fewer data points.

The paper tackles fair representation learning by smoothing feature mappings.

With ever-increasing computational demand for deep learning, it is critical to investigate the implications of the numeric representation and precision of DNN model weights and activations on computational efficiency. In this work, we explore unconventional narrow-precision floating-point representations as it relates …

Graph embedding is a central problem in social network analysis and many other applications, aiming to learn the vector representation for each node. While most existing approaches need to specify the neighborhood and the dependence form to the neighborhood, which may significantly degrades the flexibility of represent…

Training of large-scale deep neural networks is often constrained by the available computational resources. We study the effect of limited precision data representation and computation on neural network training. Within the context of low-precision fixed-point computations, we observe the rounding scheme to play a cruc…

A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network's width is increased. Recent evidence suggests that developing compressible representations is key for adjusting the complexity of large networks to the learning task at hand. However, t…

CausalCOMRL improves RL task representations by integrating causal relationships, enhancing generalizability.

We create a smooth manifold of triangular meshes with a geodesically complete metric.

This paper tackles noise in raw datasets to improve representation learning efficiency.

Statistical test detects model degradations in optimized language models.

Low-precision representation of deep neural networks (DNNs) is critical for efficient deployment of deep learning application on embedded platforms, however, converting the network to low precision degrades its performance. Crucially, networks that are designed for embedded applications usually suffer from increased de…

Binary representation is desirable for its memory efficiency, computation speed and robustness. In this paper, we propose adjustable bounded rectifiers to learn binary representations for deep neural networks. While hard constraining representations across layers to be binary makes training unreasonably difficult, we s…

New framework analyzes why more negative samples improve self-supervised learning performance.

BNCR-GAN improves GANs to generate clean images from degraded inputs.

Neural network predicts electrochemical cell faults with 53% less error.

New metrics reveal oversmoothing in GNNs more accurately than traditional methods.

Framework optimizes battery storage for markets by separating long-term degradation from short-term market dynamics.

Simplified trust region method reduces representation change during fine-tuning.

TPA-AD detects axle-box bearing anomalies using pseudo anomalies near normal boundaries.

It is a key to construct a similarity graph in graph-oriented subspace learning and clustering. In a similarity graph, each vertex denotes a data point and the edge weight represents the similarity between two points. There are two popular schemes to construct a similarity graph, i.e., pairwise distance based scheme an…

Paper develops a hybrid DNN approach for RUL prediction with adaptive drift.

A method for inferring ground-truth signals from degraded sensor data.

Study investigates how errors in reinsurance parameters degrade optimal solutions.

Paper uses neural networks to predict NOx emissions from gas turbines.

Paper develops a method to robustly cluster tensors with outliers.

Sparse molecular representations improve interpretability in graph neural networks.

Paper proposes a new model for speech synthesis with better interpretability.

Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length representation from a variable-length input sentence, and the decoder generates…

LDReg addresses local dimensional collapse in self-supervised learning.

Empirical mode modeling improves state-space analysis of noisy data.

In the past years, Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation cost have become the main obstacle for deployment of such powerful algorithm in the low power and resource-limited mobile systems. As the c…

Universal model for soft tissue mechanics under shock waves.

Kernel ridge regression is used to approximate the kinetic energy of non-interacting fermions in a one-dimensional box as a functional of their density. The properties of different kernels and methods of cross-validation are explored, and highly accurate energies are achieved. Accurate {\em constrained optimal densitie…

Paper predicts bearing degradation stages for pharmaceutical industry maintenance.

Paper proposes a new regularization method to prevent model degradation under distribution shifts.

Analyzes layer-wise quantization effects in neural networks.

RNNs solve modular addition tasks using low rank and sparse Fourier structures.

Theory models nonlinear soft tissue elasticity and remodeling using extended Finsler geometry.

Deep RL for portfolio management shows poor robustness.