Proves deep networks can learn hierarchical structures efficiently.
problem Understanding how deep networks learn hierarchical structures in data.
method Random Hierarchy Models, gradient-based methods, layerwise training.
result Proves deep networks can efficiently learn hierarchical structures.
Improved hierarchical discrete VAEs for better stability and performance.
problem Training stable and efficient hierarchical discrete VAEs with numerous latent variables.
method Introducing Relaxed-Responsibility Vector-Quantisation to parameterise discrete latent variables in a hierarchical structure.
result Achieved state-of-the-art bits-per-dim results for various standard datasets.
Graph Pointer Networks and hierarchical reinforcement learning solve combinatorial optimization problems like TSP.
problem Traveling Salesman Problem (TSP) with constraints.
method Graph Pointer Networks (GPNs) and hierarchical reinforcement learning.
result GPNs and hierarchical RL find optimal solutions for TSP and TSP with time windows.
Proposes EM-HRNN model for better hierarchical language representation.
problem Learning hierarchical representations in natural language processing.
method Introduces latent indicator layer and EM algorithm for training.
result EM-HRNN model outperforms other RNN-based models in document classification.
This paper explains how deep learning performs hierarchical learning efficiently.
problem How deep learning can perform hierarchical learning efficiently.
method Backward feature correction principle and SGD training.
result Deep learning can efficiently train complex hierarchical tasks using SGD.
This work improves metric learning models by incorporating class hierarchies.
problem Class hierarchies are often ignored in classification-based metric learning models.
method Trained softmax classifier and metric learning models with predefined class hierarchies.
result ProxyDR model performs better in hierarchical inference and hierarchy-informed performance.
Generative model learns hierarchical structure for better sample diversity.
problem Generating high-quality samples from arbitrary distributions.
method Hierarchical mixtures of generators inspired by hierarchical mixture of experts.
result Hierarchical model generates high-quality and diverse samples.
Improved deep hierarchical VAE with diffusion-based VampPrior.
problem Latent variable generative modeling challenges.
method Hierarchical VAE with amortized diffusion-based VampPrior.
result Better performance with fewer parameters and improved stability.
New hierarchical VQ-VAE scheme improves image compression quality and features at low bitrates.
problem Low bitrate image compression maintaining quality and features.
method Hierarchical VQ-VAE with stochastic quantization and Markovian latent variables.
result High perceptual quality and semantic features at low bitrates.
Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a higher level that controls the skills in a new task. Leaving the skills fixed can le…
Sharp theory of neural network scaling laws for hierarchical targets.
problem Learning hierarchical multi-index models in neural networks.
method Sharp information-theoretic scaling laws derived for two-layer neural networks.
result Optimal rates achieved by a simple spectral estimator.
Improved simulation of phase transitions using hierarchical autoregressive networks.
problem Simulating phase transitions in complex systems.
method Hierarchical Autoregressive Neural (HAN) network sampling algorithm.
result Significant improvement in statistical uncertainty compared to the Wolff cluster algorithm.
Variational inference improves hierarchical imitation learning of control programs.
problem Learning structured control policies from demonstrations.
method Variational inference for discovering hierarchical structure in observation-action traces.
result Variational inference leads to more efficient and generalized control policies.
Two new estimators improve VAE training for hierarchical and prior parameters.
problem Efficient gradient estimation for VAEs with hierarchical and prior parameters.
method Developed two generalizations of Doubly-Reparameterized Gradient Estimators (DReGs) for VAEs.
result Improved training of conditional and hierarchical VAEs on image modeling tasks.
We present Multitask Soft Option Learning(MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational posteriors for each task, regularized by a shared prior. This ''soft'' version of options avoids several instabilities during training in a …
New method explains classifiers trained on raw hierarchical data.
problem Lack of interpretability in classifiers trained on raw structured data.
method Treating classifiers as subset selection problems, generating interpretable explanations efficiently.
result Computational efficiency and higher-quality explanations compared to existing methods.
Over the past decade, Deep Convolutional Neural Networks (DCNNs) have shown remarkable performance in most computer vision tasks. These tasks traditionally use a fixed dataset, and the model, once trained, is deployed as is. Adding new information to such a model presents a challenge due to complex training issues, suc…
Deep networks learn hierarchical functions more efficiently than shallow ones.
problem Understanding the advantage of deep neural networks over shallow models.
method Analytical study of learning dynamics and generalization performance of deep networks compared to shallow ones.
result Deep networks reduce effective dimensionality, enabling learning with fewer samples.
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which …
BoRA finetunes multi-task LLMs by sharing information through hierarchical priors.
problem Limited data for some tasks in multi-task LLMs.
method Bayesian hierarchical low-rank adaption.
result BoRA outperforms individual and unified model approaches.
Paper tackles brain tumor segmentation using weak labels and hierarchical training.
problem High manual labeling effort for fully supervised brain tumor segmentation.
method Uses scribbles and global labels for weak supervision, trains two networks in phases.
result Achieves competitive results on brain tumor segmentation and substructure segmentation.
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 explore two extensions of one such model, the order-embedding model for hierarchical…
Paper proposes a new hierarchical attention mechanism for multi-scale data.
problem Challenges in applying neural attention to multi-scale, multi-modal data.
method Developed a mathematical framework for multi-modal, multi-scale data and derived optimal neural attention mechanics.
result Proposed hierarchical attention mechanism improves transformer performance in multi-scale, multi-modal settings.
Deep neural networks have been shown to be very successful at learning feature hierarchies in supervised learning tasks. Generative models, on the other hand, have benefited less from hierarchical models with multiple layers of latent variables. In this paper, we prove that hierarchical latent variable models do not ta…
In supervised clustering, standard techniques for learning a pairwise dissimilarity function often suffer from a discrepancy between the training and clustering objectives, leading to poor cluster quality. Rectifying this discrepancy necessitates matching the procedure for training the dissimilarity function to the clu…
Deep learning models based on CNNs are predominantly used in image classification tasks. Such approaches, assuming independence of object categories, normally use a CNN as a feature learner and apply a flat classifier on top of it. Object classes in many settings have hierarchical relations, and classifiers exploiting …
Paper proposes a GPU-based system for training massive deep learning models in ads systems.
problem Training massive deep learning models with terabyte-scale parameters in ads systems.
method Hierarchical GPU parameter server with 3-layer storage (GPU High-Bandwidth Memory, CPU main memory, SSD).
result 4-node hierarchical GPU parameter server trains a model 2X faster than a 150-node in-memory system.
Diffusion models learn hierarchical composition rules from data.
problem How many samples do generative models need to learn hierarchical composition rules?
method Theoretical and empirical investigation of diffusion models on probabilistic context-free grammars.
result Diffusion models learn hierarchical composition rules with sample complexity scaling polynomially with context size.
Deep generative models have achieved great success in unsupervised learning with the ability to capture complex nonlinear relationships between latent generating factors and observations. Among them, a factorized hierarchical variational autoencoder (FHVAE) is a variational inference-based model that formulates a hiera…
New hierarchical tensor decomposition model for complex data.
problem Lack of natural generalization of hierarchical NMF to tensors.
method Proposes a new hierarchical nonnegative tensor decomposition (HNTF) model.
result Model more naturally illuminates topic hierarchy.
New measure shows how LSTM models compose hierarchical representations.
problem Understanding how LSTM models capture compositional structure in language.
method Novel measure of interdependence between word meanings in LSTM internal gates.
result High interdependence can hurt generalization and reveals hierarchical structure learning.
Federated Learning speeds up speech recognition training by 7x and reduces error rate by 6%.
problem Training acoustic models for speech recognition tasks in a federated manner.
method Hierarchical optimization and dynamic gradient aggregation methods.
result Significant improvement in training convergence speed and model performance.
GANs can learn hierarchical distributions in real-world images efficiently.
problem Understanding and efficiently learning complex, real-world distributions with GANs.
method Formally studying how GANs can learn hierarchically generated distributions close to real-life image distributions using SGDA.
result Training GANs via SGDA can efficiently learn distributions with a 'forward super-resolution' structure, both in sample and time complexities.
The paper introduces an adjacency constraint to improve goal-conditioned HRL.
problem Training inefficiency in goal-conditioned HRL due to large action space.
method Restricting the high-level action space to a k-step adjacent region of the current state.
result The adjacency constraint preserves optimal hierarchical policies and improves HRL performance.
A new method generates graphs with hierarchical structures.
problem Generating graphs with natural hierarchical structures.
method Recursively generates community structures at multiple resolutions, parallel generation of all sub-structures.
result Improves generative performance on multiple graph datasets.
Variational dropout (VD) is a generalization of Gaussian dropout, which aims at inferring the posterior of network weights based on a log-uniform prior on them to learn these weights as well as dropout rate simultaneously. The log-uniform prior not only interprets the regularization capacity of Gaussian dropout in netw…
Unified tensor model disentangles object appearance factors.
problem Representing hierarchical intrinsic and extrinsic causal factors of object appearance.
method Compositional hierarchical tensor factorization.
result Interpretable object representation robust to occlusion and reduced training data requirements.
Probabilistic label trees improve XMLC by organizing labels hierarchically.
problem Efficiently tagging instances with a small subset of relevant labels from a large pool.
method Introduce and analyze probabilistic label trees (PLTs) as a generalization of hierarchical softmax for multi-label problems.
result PLTs are consistent for various performance metrics and can be trained online without prior knowledge.
Method learns domain-specific representations without supervision.
problem Domain generalization without labeled data.
method Hierarchical variational autoencoder approach.
result Model generalizes to unseen domains without domain supervision.
Efficiently trains deep Gaussian processes with sparse approximations.
problem High computational complexity in training and inference for DGP models.
method Tensor Markov Gaussian Processes (TMGP) and hierarchical expansion to create DTMGP model.
result DTMGP model achieves superior computational efficiency compared to existing DGP models.
Diffusion models generalize better with hierarchical data structure and regularization.
problem Understanding generalization in diffusion models with finite data.
method Analyzing diffusion models through data covariance spectra and developing a theoretical framework based on linear neural networks.
result Generalization in diffusion models improves with hierarchical data structure and regularization.
Proposes a hierarchical curriculum loss to improve model accuracy and interpretability.
problem Flat label spaces in classification algorithms fail to capture dependencies in real-world data.
method Introduces hierarchical curriculum loss with two properties: satisfying hierarchical constraints and providing non-uniform label weights.
result The proposed loss function significantly outperforms multiple baselines on real-world image datasets.
Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain data. In recent years, many researchers have used deep neural network models for c…
Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing to a number of intuitive benefits, including learning over temporally extended transitions, exploring over temporally extended …
Hierarchical neural networks are exponentially more efficient than their corresponding "shallow" counterpart with the same expressive power, but involve huge number of parameters and require tedious amounts of training. Our main idea is to mathematically understand and describe the hierarchical structure of feedforward…
BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.
problem Accurate inflation forecasting is challenging due to dynamic factors and the layered structure of the Consumer Price Index.
method Bi-directional Hierarchical Recurrent Neural Network (BiHRNN) model that uses bidirectional information flow between levels and informative constraints on RNN parameters.
result BiHRNN significantly outperforms traditional RNN models in forecasting accuracy.
Framework harmonizes EHR data across institutions for better analysis.
problem Heterogeneity of medical codes and terminologies hinder EHR data analysis.
method MASH (Multi-source Automated Structured Hierarchy) uses neural optimal transport and learned hyperbolic embeddings to align and structure EHR data.
result MASH generates interpretable hierarchical graphs for unstructured local laboratory codes.
A novel beam training scheme optimizes multi-hop THz communications with up to 75% performance gain.
problem Optimizing beam training for multi-hop THz communications with high data rates and low time overhead.
method Developed a reinforcement learning-based hierarchical beam training scheme with dynamic training levels.
result The proposed scheme achieves up to 75% performance gain in spectral efficiency compared to conventional methods.