Contrastive embeddings improve neural architecture search performance.
problem Improving performance of neural architecture search algorithms.
method Contrastive learning to identify networks based on data Jacobians and produce embeddings.
result Traditional black-box optimization algorithms can reach state-of-the-art performance with contrastive embeddings.
Smooth embedding space improves NAS performance.
problem Efficiently predicting good neural architectures.
method Two-sided variational graph autoencoder.
result Smooth embedding space facilitates extrapolation to unseen architectures.
The neural architecture search (NAS) algorithm with reinforcement learning can be a powerful and novel framework for the automatic discovering process of neural architectures. However, its application is restricted by noncontinuous and high-dimensional search spaces, which result in difficulty in optimization. To resol…
New lower bounds on embedding dimensions for neural network architectures.
problem Ensuring neural networks can handle symmetries like permutations in high dimensions.
method Novel technique to prove lower bounds on embedding dimensions.
result Proves new lower bounds on embedding dimensions for Deep Sets and Janossy pooling.
Interstellar searches for recurrent architecture to enhance KG embedding.
problem Learning long-term information in KGs.
method Recurrent neural architecture search for relational paths.
result Effectiveness and efficiency of searched models.
MMbeddings reduces categorical embeddings by treating them as latent effects, significantly decreasing parameters and mitigating overfitting.
problem Large cardinalities in categorical embeddings lead to high parameter counts and overfitting.
method MMbeddings treats embeddings as latent random effects in a variational autoencoder framework, reducing parameter count and mitigating overfitting.
result MMbeddings consistently outperforms traditional embeddings across various tasks, demonstrating its potential in machine learning applications.
AutoEmbedder clusters unlabeled data using semi-supervised DNN embedding.
problem Clustering unlabeled data efficiently and effectively.
method Semi-supervised DNN embedding system using Siamese network architecture.
result AutoEmbedder outperforms existing DNN-based semi-supervised methods.
Ring-reservoir networks simplify graph embeddings efficiently.
problem Efficient graph embeddings using deep neural networks.
method Progressive simplification of Reservoir Computing models to ring topology.
result Ring-reservoir networks show consistent advantages in predictive performance.
The recent advances in deep neural networks (DNNs) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-constrained computing devices. Model compression techniques can address the computation issue of deep inference on embedded devices. This technique is …
We address the problem of domain generalization where a decision function is learned from the data of several related domains, and the goal is to apply it on an unseen domain successfully. It is assumed that there is plenty of labeled data available in source domains (also called as training domain), but no labeled dat…
This study compares mtl architectures for renewable power generation forecasting.
problem Forecasting expected power generation for renewable power plants.
method Comparative study of mtl architectures including Hard parameter sharing, cross-stitch network, sluice network, and task embedding.
result Emerging Relation Network (ERN) and task embedding provide significant improvements in forecasting.
AutoML uses dataset and algorithm descriptions to improve performance.
problem Improving automated machine learning performance.
method Uses language embeddings to augment AutoML recommendations.
result Zero-shot AutoML system provides good solutions in under a second.
New approach reduces model size for Transformer architectures.
problem Large embedding dimensions limit model applicability.
method Identified low-rank bottleneck in multi-head attention.
result Reducing head size to sequence length improves model performance.
A brain can detect outlier just by using only normal samples. Similarly, one-class classification (OCC) also uses only normal samples to train the model and trained model can be used for outlier detection. In this paper, a multi-layer architecture for OCC is proposed by stacking various Graph-Embedded Kernel Ridge Regr…
Models use embeddings and attention for better claim severity prediction.
problem Improving predictive modeling of claim severity with categorical data.
method Developed neural networks and attention-based architectures with embeddings.
result Attention-based models enhance predictive performance with contextual augmentation.
We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult to parallelize. We take a different route and develop a convolutional neural network (CNN) embedding model. Our CNN architecture is fully par…
Boosted embeddings improve time series forecasting models.
problem Improving time series forecasting accuracy.
method Gradient boosting with DNN weak learners and incremental weight updates.
result DeepGB model outperforms state-of-the-art models.
In this paper we study the real time deployment of deep learning algorithms in low resource computational environments. As the use case, we compare the accuracy and speed of neural networks for smile detection using different neural network architectures and their system level implementation on NVidia Jetson embedded p…
Automatic neural architecture design has shown its potential in discovering powerful neural network architectures. Existing methods, no matter based on reinforcement learning or evolutionary algorithms (EA), conduct architecture search in a discrete space, which is highly inefficient. In this paper, we propose a simple…
Explores tensor products in hyperdimensional computing.
problem Understanding tensor products in hyperdimensional computing.
method Generalized results from graph embeddings to vector symbolic architectures and hyperdimensional computing.
result Tensor product is the most general and expressive representation with errorless unbinding and detection.
We introduce a novel encoder-decoder architecture to embed functional processes into latent vector spaces. This embedding can then be decoded to sample the encoded functions over any arbitrary domain. This autoencoder generalizes the recently introduced Conditional Neural Process (CNP) model of random processes. Our ar…
A novel GNN architecture improves link prediction by combining positive and negative samples.
problem Link prediction accuracy limited by node-wise methods and increased model complexity of edge-wise methods.
method Proposes a novel GNN architecture that uses both positive and negative samples to inform node embeddings.
result The method retains the inference speed of node-wise models while achieving competitive accuracy with edge-wise alternatives.
Study evaluates 21 KG embedding models, highlighting model architecture, training approach, and loss function importance.
problem Difficulty in fair and thorough comparisons of knowledge graph embedding models due to heterogeneity in implementations, training, and evaluation.
method Reimplemented and evaluated 21 models in PyKEEN, providing insights into reproducibility and best practices.
result Best practices and configurations for each model were identified, showing the importance of model architecture, training approach, and loss function.
We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedd…
Embedded ensembles improve neural network performance efficiently.
problem Improving neural network performance with fewer resources.
method Analyzing the wide network limit of gradient descent dynamics using Neural-Tangent-Kernel.
result Embedded ensembles exhibit two regimes: independent and collective, affecting performance.
PoET-BiN reduces power consumption in neural networks on embedded devices.
problem Power inefficiency in neural network implementations on embedded platforms.
method Look-Up Table based implementation with a modified Decision Tree approach.
result Near state-of-the-art results with up to 6 orders of magnitude energy reduction.
We propose a novel architecture for k-shot classification on the Omniglot dataset. Building on prototypical networks, we extend their architecture to what we call Gaussian prototypical networks. Prototypical networks learn a map between images and embedding vectors, and use their clustering for classification. In our…
LaT-PFN model predicts time series with zero-shot capability.
problem Zero-shot time series forecasting.
method In-context latent space learning with JEPA and PFN integration.
result Superior zero-shot predictions compared to baselines.
Attention improves edge prediction in e-commerce graphs.
problem Predicting edges in graphs from node attributes in e-commerce.
method Used attention mechanism in simple feedforward networks, derived analytically tractable model AttEST.
result Attention network outperforms LSTM architectures by over 20% on F-1 score.
Word2Vec (W2V) and GloVe are popular, fast and efficient word embedding algorithms. Their embeddings are widely used and perform well on a variety of natural language processing tasks. Moreover, W2V has recently been adopted in the field of graph embedding, where it underpins several leading algorithms. However, despit…
DEN learns diverse tasks to generalize to unseen tasks.
problem Generalization from a diverse set of classification tasks with limited data.
method Three-block architecture: covariate transformation, distribution embedding, and classification.
result DEN outperforms existing methods in various synthetic and real tasks.
Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (MKL) attempt to learn the parameters for combining the kernels through sophisticated optimization procedures. In this paper, we propose an a…
Enhances LightGCN for credit bond recommendations with dynamic node embeddings.
problem Challenges in static embeddings for rapidly evolving user interests in finance.
method Causal graph convolution for dynamic node embeddings over chronological user-item interactions.
result Significantly enhances LightGCN performance in financial product recommendations.
LeJEPA provides a scalable, theory-driven approach to self-supervised learning.
problem Lack of practical guidance and theory in JEPAs.
method Identified optimal Gaussian distribution and introduced SIGReg objective.
result LeJEPA achieves state-of-the-art performance with minimal hyperparameters and heuristics.
Embedding representations power machine intelligence in many applications, including recommendation systems, but they are space intensive -- potentially occupying hundreds of gigabytes in large-scale settings. To help manage this outsized memory consumption, we explore mixed dimension embeddings, an embedding layer arc…
Recent work has demonstrated that embeddings of tree-like graphs in hyperbolic space surpass their Euclidean counterparts in performance by a large margin. Inspired by these results and scale-free structure in the word co-occurrence graph, we present an algorithm for learning word embeddings in hyperbolic space from fr…
Improved molecular property prediction using WL embedding in GNNs.
problem Limited performance of GNNs in predicting molecular properties.
method Explored Weisfeiler-Lehman (WL) embedding to replace GNN layers, enhancing representability and performance.
result WL embedding consistently improves GNN performance across multiple datasets.
Proposes neural networks that preserve physical system dynamics.
problem Learning accurate representations of dynamical systems.
method Variational integrator networks designed to preserve geometric structure.
result Accurately learns dynamical systems from noisy observations.
New framework for manifold convolutions using toric embeddings.
problem Computational intractability of manifold convolutions.
method Isometric embeddings into tori for global manifold convolutions.
result Global definition of manifold convolutions on finite approximations.
End-to-end dialogue model learns from joint embeddings and user intent.
problem Challenges in reasoning and incorporating state-full knowledge in goal-oriented dialogues.
method Proposes an RNN-based end-to-end encoder-decoder architecture trained with joint embeddings and multi-task learning.
result Improves task-oriented dialogue system performance as shown by BLEU score evaluation.
Automatic cover detection -- the task of finding in an audio database all the covers of one or several query tracks -- has long been seen as a challenging theoretical problem in the MIR community and as an acute practical problem for authors and composers societies. Original algorithms proposed for this task have prove…
Monitoring the biomedical literature for cases of Adverse Drug Reactions (ADRs) is a critically important and time consuming task in pharmacovigilance. The development of computer assisted approaches to aid this process in different forms has been the subject of many recent works. One particular area that has shown pro…
A neural network learns phase space properties for time series analysis.
problem Lack of consistency and robustness in estimating embedding parameters.
method Forgetting mechanism neural network to learn phase space properties.
result Neural network approach is competitive or superior to state-of-the-art strategies.
Enhanced word embeddings boost multiclass text classification accuracy.
problem Improving multiclass text classification accuracy using pre-trained embeddings.
method Proposed word-class embeddings (WCEs) to enhance pre-trained word embeddings.
result WCEs significantly improve multiclass text classification accuracy.
Lyapunov analysis improves RNN performance prediction.
problem Uncertainty in RNN performance prediction due to hyperparameters and architecture.
method Lyapunov spectral analysis of RNNs and Autoencoder-Lyapunov Embedding Learning (AeLLE).
result AeLLE successfully correlates RNN Lyapunov spectrum with accuracy and predicts performance.
BERT embeddings improve sequence quality metrics.
problem Measuring the quality of generated sequences against references.
method Employ contextual BERT embeddings for sequence-level reward.
result Contextual embeddings provide a more effective learning signal.
MixerFlow combines MLP-Mixer with normalizing flows for efficient image modeling.
problem Efficiently modeling complex image densities using generative models.
method Proposes MixerFlow, a novel architecture based on MLP-Mixer for normalizing flows.
result Demonstrates improved density estimation and better scaling with higher image resolutions.
LASE learns graph embeddings by unrolling GD iterations into a neural network.
problem Learning graph embeddings from graph inputs.
method Truncating and interpreting GD iterations as layers in a GNN.
result LASE outperforms eigendecomposition routines and GNNs in link prediction and node classification.