Model learns sub-goals and low-level policies for hierarchical reinforcement learning.
problem Determining appropriate low-level policies in hierarchical reinforcement learning.
method Unsupervised learning scheme based on asymmetric self-play.
result Obtains performance gains over non-hierarchical approaches.
New method tackles catastrophic forgetting and order-sensitivity in continual learning.
problem Catastrophic forgetting and order-sensitivity in continual learning.
method Additive Parameter Decomposition (APD) to represent task parameters as a sum of shared and adaptive parts.
result Significantly outperforms state-of-the-art methods in accuracy, scalability, and order-robustness.
End-to-end autonomous driving framework using guided auxiliary supervision.
problem Learning to drive in highly stochastic urban settings.
method Multi-task Learning from Demonstration (MT-LfD) framework with end-to-end trainable network and supervised auxiliary tasks.
result Joint learning and supervised guidance facilitate faster and better driving performance.
HCL learns shared and modality-specific latent representations for multimodal data.
problem Binary shared-private decomposition inadequately represents shared information across subsets of modalities.
method Hierarchical Contrastive Learning framework combining latent-variable formulation, structural sparsity, and contrastive objective.
result HCL accurately recovers hierarchical structure and improves predictive performance on multimodal data.
HiDe learns hierarchical control for complex tasks by separating planning and control.
problem Solving long horizon control tasks with generalization to unseen scenarios.
method Functional decomposition of state-action spaces, RL-based planner, modular transfer of policy layers.
result Generalizes across unseen test environments and scales to longer horizons.
This paper improves neural network explanations by quantifying and visualizing semantic compositions.
problem Improving neural network explanations for natural language processing tasks.
method Proposes a formal way to quantify word and phrase importance, introduces SCD and SOC algorithms.
result Our algorithms outperform prior methods in explaining neural network predictions.
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.
Paper compresses RNNs using HT decomposition for better performance.
problem Large model sizes of RNNs in sequence analysis.
method Hierarchical Tucker (HT) tensor decomposition for model compression.
result HT-LSTM achieves better compression and accuracy than state-of-the-art methods.
Robot learns multiple tasks hierarchically by transferring knowledge.
problem Learning multiple complex tasks in open-ended environments.
method Task-oriented procedures, goal-babbling, imitation learning, active learning, intrinsic motivation.
result Robots can learn complex tasks more efficiently by transferring knowledge from simpler ones.
Novel method extracts hierarchical brain connectivity patterns from fMRI.
problem Functional hierarchical organization of the human brain.
method Sparse Connectivity Patterns (SCPs) with hierarchy of sparse overlapping patterns, deep factorization of correlation matrices.
result Reproducible multi-scale hierarchical SCPs more stable than single-scale patterns.
Eikonal-Constrained QRL improves goal-reaching in reinforcement learning.
problem Reward design and out-of-distribution generalization in reinforcement learning.
method Eikonal-Constrained Quasimetric Reinforcement Learning (Eik-QRL) using the Eikonal PDE.
result Eik-QRL achieves state-of-the-art performance in offline goal-conditioned navigation and manipulation tasks.
New method groups genetic data into coherent topics for disease insights.
problem Analyzing large, multi-dimensional genetic data sets.
method Conditional Hierarchical Bayesian Tucker Decomposition for genetic data analysis.
result Our models are more coherent than baseline models.
TreeHFD algorithm explains tree ensemble models through hierarchical orthogonality.
problem Difficulty in explaining black-box tree ensemble models.
method TreeHFD algorithm using hierarchical orthogonality constraints.
result TreeHFD estimates Hoeffding decomposition from data samples.
New method explains ML performance gaps without causal knowledge.
problem Understanding why ML algorithms perform differently across domains.
method Nonparametric hierarchical decomposition framework.
result Detailed variable-level explanations for performance gaps.
We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in kernel methods, enabling nested part-of-part relations. Unlike recursive neural networks, which unroll a template on input graphs directly, we…
Outer automorphism group of hyperbolic groups is HHG under certain conditions.
problem Characterizing the outer automorphism group of hyperbolic groups.
method Proving finite-index subgroups are central extensions of orbifold mapping class groups with bounded Euler class.
result Outer automorphism group of a one-ended hyperbolic group is virtually a hierarchically hyperbolic group.
Neurally-Guided Structure Inference combines search and data-driven methods for efficient, robust structure inference.
problem Combining the advantages of exhaustive search and data-driven methods for structure inference.
method Neurally-Guided Structure Inference (NG-SI) uses a neural network to guide hierarchical search over structures.
result NG-SI outperforms search-based and data-driven methods on probabilistic matrix decomposition and symbolic program parsing.
Proposes a method to interpret neural networks via hierarchical modular representation.
problem Lack of prior knowledge about optimal resolution and cluster number, and inability to assess cluster outputs' correlation with inputs and outputs.
method Proposes a hierarchical clustering method to reveal a tree-structured relationship among hidden layer units based on their feature vectors.
result Reveals a hierarchical modular representation of a layered neural network, providing insights into the network's structure and function.
RICH models scenes as hierarchical tree to learn and generate complex compositions.
problem Learning compositional structures between parts and objects in natural scenes.
method RICH uses a latent scene graph to organize entities into a tree structure and employs a top-down inference approach.
result RICH learns and generates complex scene hierarchies from unlabeled data.
In this work, we provide theoretical guarantees for reward decomposition in deterministic MDPs. Reward decomposition is a special case of Hierarchical Reinforcement Learning, that allows one to learn many policies in parallel and combine them into a composite solution. Our approach builds on mapping this problem into a…
Novel graph network learns hierarchical network structure.
problem Lack of information in hierarchical network topology.
method Hierarchical clustering for multiscale decomposition, graph convolutional layers.
result Competitive performance on citation network benchmark.
A new method uses CPD to efficiently model feature interactions in non-sequential data.
problem Efficiently modeling feature interactions in non-sequential data with high computational and memory costs.
method Implicitly represent model parameters as a tensor, factorize into a compact Tensor Train (TT) format, and use Canonical Polyadic (CP) Decomposition for invariance to feature ordering.
result The proposed CP-based predictor outperforms other TN-based predictors on sparse data and matches neural network performance on dense non-sequential tasks.
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 introduces hierarchical softmax for global hierarchical classification tasks.
problem Improving classification accuracy in tasks with class hierarchies.
method Global hierarchical neural networks using hierarchical softmax.
result Hierarchical softmax outperforms regular softmax in multiple datasets.
Improved spectral methods of moments for robust latent variable model learning.
problem Limited robustness of spectral methods of moments to model misspecification.
method Hierarchical approach using approximate joint diagonalization instead of tensor decomposition.
result Our method outperforms previous tensor decomposition methods in speed and model quality.
NeuroMAS treats multi-agent systems as neural networks for scalable, trainable coordination.
problem Designing multi-agent systems as hand-designed workflows is inefficient and inflexible.
method NeuroMAS treats multi-agent systems as a neural network architecture with reinforcement learning for scalable coordination.
result NeuroMAS improves significantly over multi-agent baselines and can be scaled progressively.
HSML tailors meta-learning knowledge to task clusters.
problem Handling task uncertainty and heterogeneity in meta-learning.
method Gradient-based HSML with hierarchical task clustering.
result HSML achieves state-of-the-art performance in few-shot learning.
Unified algorithm for tensor decomposition supports multiple loss functions and models.
problem Efficient tensor decomposition for various models and loss functions.
method Hierarchical combination of ADMM and MM for optimization.
result Wide-range applications can be solved by the proposed algorithm.
Hierarchical RL simplifies exploration in RL tasks.
problem Why does hierarchy work well in RL?
method Evaluated hierarchical RL on various tasks, focusing on exploration benefits.
result Most benefits of hierarchy can be attributed to improved exploration.
A new HRL method learns hierarchical policies using mutual information maximization.
problem Learning hierarchical policies in reinforcement learning for structured tasks.
method Mutual information maximization for latent variable learning, advantage-weighted importance sampling for option policies, deterministic policy gradient for optimization.
result Enhanced performance in continuous control tasks through learned hierarchical policies.
MSOL learns hierarchical policies for multitask tasks with soft options.
problem Training hierarchical policies for multiple tasks with stability and flexibility.
method MSOL uses separate variational posteriors for each task, regularized by a shared prior, to avoid instabilities and fine-tune options for new tasks.
result MSOL significantly outperforms hierarchical and flat transfer-learning baselines.
We improve learning sub-tasks in hierarchical reinforcement learning using hyperbolic embeddings.
problem Learning meaningful sub-tasks in hierarchical reinforcement learning remains challenging.
method Combining routing in computer networks and graph-based skill discovery, we use hyperbolic embeddings to define sub-goals.
result Hyperbolic embeddings enforce a global topology on states, enabling the learning of meaningful sub-tasks.
Boxhead dataset tests autoencoder disentanglement in hierarchical data.
problem Evaluate disentanglement in hierarchical data.
method Introduced Boxhead dataset with hierarchically structured factors, evaluated autoencoder models.
result Hierarchical models outperform single-layer VAEs in disentangling factors.
New method approximates high-dimensional probability densities efficiently.
problem Approximating high-dimensional probability densities accurately and efficiently.
method Hierarchical tensor-network approach using randomized SVD and linear equations.
result The method effectively approximates high-dimensional densities with linear complexity.
SHAKE-GNN scales GNNs for large graphs with multi-scale representations.
problem Scaling Graph Neural Networks (GNNs) to large graphs.
method SHAKE-GNN uses a hierarchy of Kirchhoff Forests for stochastic multi-resolution graph decompositions.
result SHAKE-GNN achieves competitive performance on large-scale graph classification benchmarks.
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…
Convolutional networks outperform shallow classifiers on certain tasks due to hierarchical structure.
problem Understanding why convolutional networks outperform shallow classifiers on specific tasks.
method Approximation theory, visual tasks with deterministic scrambling, and network performance evaluation.
result Hierarchical structure is crucial for convolutional networks' performance on certain tasks, but not all.
New algorithm learns sub-task policies from unsegmented demonstrations.
problem Challenges in learning hierarchical policies from unsegmented demonstrations.
method Generative adversarial imitation learning framework with directed information maximization.
result Automatic learning of sub-task policies from unsegmented demonstrations.
Hierarchical Softmax approximates class probabilities for large datasets efficiently.
problem Computational inefficiency of Softmax for large-scale classification tasks.
method Used Hierarchical Softmax to approximate class probabilities efficiently.
result Hierarchical Softmax performance degrades as the number of classes increases.
Proposes polynomial neural networks for improved function approximation in various tasks.
problem Improving function approximation in various tasks like image generation, face verification, and 3D mesh representation learning.
method Introduces polynomial neural networks (Π-Nets) and three tensor decompositions to reduce parameter count and enhance expressiveness. result Demonstrates that Π-Nets can produce state-of-the-art results in challenging tasks without non-linear activation functions. Proposes a model for multi-agent reinforcement learning with hierarchical graph attention network.
problem Limited transferability of trained policies to new multi-agent tasks.
method Uses hierarchical graph attention network for representation learning and multi-agent actor-critic for policy learning.
result Demonstrates superior performance in mixed cooperative and competitive tasks compared to existing methods.
RHPO improves data-efficiency for hierarchical reinforcement learning.
problem High data requirements for general reinforcement learning algorithms in robotics.
method RHPO employs compositional inductive biases and task sharing mechanisms.
result RHPO enables stable and fast learning for complex domains with positive transfer.
We propose a general framework for reduced-rank modeling of matrix-valued data. By applying a generalized nuclear norm penalty we can directly model low-dimensional latent variables associated with rows and columns. Our framework flexibly incorporates row and column features, smoothing kernels, and other sources of sid…
KT combines treelets with kernel functions for hierarchical clustering.
problem Hierarchical clustering of non-numeric data.
method Combines treelets and kernel functions to handle non-numeric data.
result KT effectively clusters non-numeric data.
Generalizes information theory for hierarchical partitions.
problem Understanding hierarchical decomposition of complex systems.
method Introducing a generalization of information theory for hierarchical partitions, revisiting Hierarchical Mutual Information (HMI), and proving its bounds and transformations.
result Derives hierarchical generalizations of information-theoretic quantities, including a non-metric variation of information.
CompILE learns reusable segments from demonstrations for hierarchical task execution.
problem Learning reusable, variable-length segments of hierarchical behavior from demonstrations.
method Unsupervised, fully-differentiable sequence segmentation module for latent encoding and re-composition.
result Model generalizes to longer sequences and unseen environments, learns task boundaries and event encodings.
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.
Improved image reconstruction and anomaly detection using hierarchical VAEs.
problem VAEs struggle with sharp images and high-level features.
method Added a new branch to hierarchical VAEs to separate high-level and low-level features.
result Results in sharper images and better anomaly detection.