Proposes SDCN to integrate structural information into deep clustering.
problem Lack of attention to structural information in representation learning for clustering.
method Designs a delivery operator to transfer autoencoder representations to GCN layers and uses a dual self-supervised mechanism.
result SDCN consistently outperforms state-of-the-art techniques in clustering tasks.
The paper proposes a deep learning technique for structured and composable representations.
problem Learning structured and composable representations from input images and discrete labels.
method End-to-end deep learning to learn representations based on distance estimates between class label and contextual information.
result The representations have a clear structure allowing for class and environment decomposition.
DS2CF-Net learns hierarchical representations with deep coupled factorization and enriched prior.
problem Learning deep hierarchical representations from data.
method Dual-constrained Deep Semi-Supervised Coupled Factorization Network (DS2CF-Net) with enriched prior.
result DS2CF-Net achieves state-of-the-art performance in representation learning and clustering.
Novel SVAE learns interpretable discrete data representations from deep learning.
problem Learning interpretable discrete data representations from deep learning.
method Structured variational autoencoder (SVAE) with novel optimization algorithms.
result First competitive comparisons with state-of-the-art time series models.
Generative concept representations improve deep learning by handling uncertainty and integrating learning and reasoning.
problem Discriminative deep learning struggles with uncertainty and lacks integration of learning and reasoning.
method Probabilistic and generative deep learning, variational autoencoders, and generative adversarial networks.
result Generative concept representations enhance deep learning by addressing these limitations.
SDREM models complex network data with deep learning, improving link prediction.
problem Modeling latent structures in relational data with high-order node dependence.
method Scalable deep generative relational model (SDREM) incorporating high-order neighbourhood structure and novel data augmentation.
result Improved link prediction performance on real-world datasets.
Method analyzes deep neural network activations to explain adversarial examples.
problem Difficulty in interpreting deep neural network representations.
method Persistent homology over graphical activation structure.
result Adversarial examples are not semantic structure additions but dominant activation structure alterations.
CRATE-MAE learns structured representations from unlabeled data.
problem Learning structured representations from unlabeled data.
method Structured Diffusion with White-Box Transformers.
result CRATE-MAE achieves highly promising performance on large-scale imagery datasets.
Machine Learning (ML) is increasingly being used for computer aided diagnosis of brain related disorders based on structural magnetic resonance imaging (MRI) data. Most of such work employs biologically and medically meaningful hand-crafted features calculated from different regions of the brain. The construction of su…
DSCF-Net learns deep features for clustering with robustness and locality preservation.
problem Unsupervised deep representation learning for clustering.
method Integrates robust deep concept factorization, deep self-expressive representation, and adaptive locality preserving feature learning.
result Delivers state-of-the-art performance on public databases.
Multimodal learning with deep Boltzmann machines (DBMs) is an generative approach to fuse multimodal inputs, and can learn the shared representation via Contrastive Divergence (CD) for classification and information retrieval tasks. However, it is a 2-fan DBM model, and cannot effectively handle multiple prediction tas…
Representation learning is a fundamental but challenging problem, especially when the distribution of data is unknown. We propose a new representation learning method, termed Structure Transfer Machine (STM), which enables feature learning process to converge at the representation expectation in a probabilistic way. We…
This paper studies nonlinear representation learning dynamics beyond the NTK regime.
problem Efficient reasoning and inference in raw sensory data representations.
method Identifies common model structure assumption and data-architecture alignment condition for global convergence and optimality.
result Theoretical framework explains network size effects and provides practical model structure guidelines.
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality of the input to the objective can greatly influence a representation's …
Improved clustering accuracy with disentangled latent code representation.
problem Improving k-Means clustering performance.
method Optimizing the entanglement of autoencoder latent code representation using soft nearest neighbor loss with annealing temperature.
result 96.2% test clustering accuracy on MNIST, 85.6% on Fashion-MNIST, and 79.2% on EMNIST Balanced datasets.
Unified framework for fair representation learning in machine learning.
problem Ensuring fairness in machine learning models, especially when biased data representations lead to unfair predictions.
method Integrates nonlinear sufficient dimension reduction with deep learning to construct fair and informative representations, introducing a penalty term to enforce conditional independence between sensitive attributes and learned representations.
result Achieves a superior balance between fairness and utility, significantly outperforming state-of-the-art baselines on various data structures.
AIDN uses deep learning to represent algebraic structures.
problem Building learning systems to uncover algebraic laws from data.
method AIDN is a deep learning algorithm that represents algebraic objects using neural networks.
result AIDN can robustly compute representations of various algebraic structures.
Proposes a deep learning framework guided by human advice.
problem Learning from sparse and noisy data.
method Knowledge-augmented Column Networks, leveraging human advice.
result Improves model performance in domains with structured representations.
Since about 100 years ago, to learn the intrinsic structure of data, many representation learning approaches have been proposed, including both linear ones and nonlinear ones, supervised ones and unsupervised ones. Particularly, deep architectures are widely applied for representation learning in recent years, and have…
New loss functions reveal layer roles in deep neural networks.
problem Understanding the role of individual layers in deep neural networks.
method Derived Deep Gaussian Layer-wise loss functions (DGLs) using Gaussian Processes and SGD.
result First explicit and competitive layer-wise loss functions for deep neural networks.
A new method learns action representations for reinforcement learning.
problem Efficient action-value estimation in reinforcement learning.
method Action hypergraph networks framework for learning action representations.
result Hypergraph Q-networks show effectiveness on various domains.
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 algorithms, we introduce a deep learning framework that supports both linear and mil…
New method uses counterfactuals to reveal modular structure in deep generative models.
problem Challenges in manipulating deep generative models' latent representations without supervision.
method Proposes a non-statistical framework based on counterfactual manipulations.
result Modules of disentangled latent variables can be used for targeted interventions.
INVERT connects neural representations to human-understandable concepts.
problem Lack of understanding and statistical significance in existing explainability methods.
method Inverse Recognition (INVERT) approach that connects learned representations to human-understandable concepts.
result INVERT provides interpretable metrics and statistical significance for representation alignment.
Deep models learn to parse complex language structures from local data patterns.
problem Understanding how deep models parse and represent language structures.
method Introduced tunable probabilistic context-free grammars and a learning algorithm inspired by deep networks.
result Data correlations across scales enable hierarchical language representations.
Deep Divergence Graph Kernels learn graph representations without supervision.
problem Learning graph representations without feature engineering or labeled graphs.
method Unsupervised method using cross-graph attention networks and divergence scores.
result Learned representations achieve competitive results on graph classification tasks.
Develops a new model for deep structured prediction with non-linear output transformations.
problem Limited neighborhood structure and inability to transform output space in deep structured models.
method Introduces a novel model that generalizes existing approaches and maintains applicability of inference techniques.
result Demonstrates improved flexibility and applicability of deep structured models through non-linear output transformations.
Geodesic clustering improves latent space clustering in deep generative models.
problem Latent representations in deep generative models distort semantic distances, making clustering difficult.
method Proposed an efficient algorithm for computing geodesics and distances in the latent space, accounting for its distortion.
result Geodesic distance reflects the internal structure of the data, improving clustering performance.
Combines global and local features for better social circle prediction in ego-networks.
problem Efficiently analyzing ego-networks with hidden local structures.
method Evolved deep learning techniques to capture both global and local network features.
result Social circle prediction benefits from a combination of global and local features.
In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a …
DeepMap learns deep graph representations via CNNs, improving graph classification performance.
problem Quantifying graph similarities for tasks like classification.
method Proposes DeepMap framework extending CNNs to arbitrary graphs, learning dense low-dimensional vectors.
result DeepMap achieves state-of-the-art performance on graph classification benchmarks.
Deep neural networks have been developed drawing inspiration from the brain visual pathway, implementing an end-to-end approach: from image data to video object classes. However building an fMRI decoder with the typical structure of Convolutional Neural Network (CNN), i.e. learning multiple level of representations, se…
Paper introduces a new framework combining deep learning and logic for relational data.
problem Scalability and flexibility of deep learning methods for relational data.
method Combines auto-encoding principle with first-order logic and logic programs.
result Latent representations are more accurate, flexible, and interpretable.
Proposes a new method to learn data representations by modeling sample relations.
problem Lack of rich latent structural information in DAEs.
method Explicitly models and leverages sample relations as supervision for representation learning.
result Significantly improves clustering performance on benchmark datasets.
p-DkNN uses deep representations to detect out-of-distribution data with statistical tests.
problem Lack of reliable confidence estimates in neural networks for safety-critical applications.
method Statistical testing of deep neural network's intermediate hidden representations.
result p-DkNN enables more accurate and reliable predictions by abstaining from incorrect predictions.
The paper explores tensor decompositions in deep learning models.
problem Compressing parameter space and creating richer representations.
method Tensor decompositions applied to deep learning models.
result Tensor methods can yield richer adaptive representations of complex data.
Deep networks learn hierarchical data by invariant representations.
problem How many examples are needed for deep networks to learn hierarchical data?
method Random Hierarchy Model: synthetic tasks inspired by language and images hierarchy.
result Deep networks learn by invariant representations and require a detectable number of correlations between low-level features and classes.
We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations. Our model stacks multiple latent GP layers to learn abstract representations of the state feature space, which is link…
New method learns representations for decision forests using input perturbation.
problem Decision forests struggle with raw structured data and lack effective representations.
method Approximate decision forest gradients through input perturbation.
result Effective representation learning for decision forests without structural changes.
Survey on deep learning for social network analysis.
problem Encoding social network data into useful low-dimensional representations.
method Review of neural network models for node and subgraph embeddings in various network types.
result Advancements in deep learning for complex network analysis.
This paper evaluates fairness in deep metric learning and proposes a method to reduce subgroup performance gaps.
problem The negative impact of deep metric learning representations on minority subgroup performance in downstream tasks.
method Definition of fairness in DML through inter-class, intra-class, and uniformity properties; finDML benchmark; Partial Attribute De-correlation (PARADE) method.
result Bias in DML representations propagates to downstream tasks, even with balanced training data.
A method combines deep learning and G-estimation for causal mediation analysis.
problem Estimating structural mediation parameters under unmeasured confounding.
method UNIT method using TARNet for representation learning and G-estimation.
result Improved precision of structural parameter estimator through better representation learning.
STDGI learns node representations for spatio-temporal graphs via mutual information maximization.
problem Challenges in learning node representations for spatio-temporal graphs due to structural changes over time.
method STDGI is a fully unsupervised approach based on mutual information maximization that exploits both spatial and temporal dynamics.
result STDGI's learned node representations improve spatio-temporal auto-regressive forecasting models.
Deep neural network predicts molecular wave functions in minimal basis.
problem Improving accuracy and efficiency in quantum chemistry calculations.
method Adapted SchNet for Orbitals (SchNOrb) model in quasi-atomic minimal basis.
result Model accurately predicts molecular orbital energies and wavefunctions for large molecules.
Deep-embedding methods aim to discover representations of a domain that make explicit the domain's class structure and thereby support few-shot learning. Disentangling methods aim to make explicit compositional or factorial structure. We combine these two active but independent lines of research and propose a new parad…
New method uses small perturbations to improve representation learning from few labels.
problem Stability issues and label scarcity in representation learning.
method Introduces small-perturbation ideology on representation probability distribution models.
result Proposed models show better performance in clustering compared to baseline methods.
This paper presents a novel deep learning-based method for learning a functional representation of mammalian neural images. The method uses a deep convolutional denoising autoencoder (CDAE) for generating an invariant, compact representation of in situ hybridization (ISH) images. While most existing methods for bio-ima…
HDGI learns node representations for heterogeneous graphs.
problem Challenges in learning node representations for heterogeneous graphs.
method HDGI uses meta-path structure, graph convolution, and semantic-level attention to maximize local-global mutual information.
result HDGI outperforms state-of-the-art methods on graph-related tasks.