MetaPerturb learns to improve generalization across different tasks and architectures.
problem Improving generalization on unseen data for diverse tasks and architectures.
method MetaPerturb is a meta-learned set-based perturbation function that improves generalization performance across heterogeneous tasks and architectures.
result MetaPerturb significantly outperforms baselines on most tasks and architectures with minimal increase in parameter size and no hyperparameters to tune.
Paper proposes NASAIC framework for co-designing neural architectures and heterogeneous ASICs.
problem Designing efficient neural architectures and ASICs for multiple tasks.
method Build ASIC templates and propose NASAIC framework for simultaneous design of architectures and ASICs.
result NASAIC ensures design specifications and maximizes accuracy with minimal performance loss.
HGT models heterogeneous graphs with dedicated node and edge representations.
problem Infeasibility of existing GNNs for heterogeneous graphs.
method Node- and edge-type dependent parameters, relative temporal encoding, heterogeneous mini-batch graph sampling.
result HGT outperforms state-of-the-art GNNs by 9%--21% on various downstream tasks.
Proposes a new method to optimize graph neural network architectures on heterogeneous information networks.
problem Weaknesses in instability and inflexibility of existing graph neural architecture search methods.
method Partial Message Meta Multigraph search (PMMM) using a differentiable framework to search for a meaningful meta multigraph.
result Significantly more stable and effective than state-of-the-art heterogeneous GNNs.
Paper tackles end-to-end training of complex neural networks using DIP method.
problem Training complex heterogeneous neural network models end-to-end.
method Deep Innovation Protection (DIP) method using multiobjective optimization.
result End-to-end training of complex heterogeneous neural network models is possible.
HeteroFL trains diverse clients with varying capabilities efficiently.
problem Training models on clients with different computational and communication capacities.
method Proposes HeteroFL framework to adaptively distribute subnetworks based on client capabilities.
result Adaptive subnetwork distribution leads to efficient computation and communication.
In this paper, we consider the problem of event classification with multi-variate time series data consisting of heterogeneous (continuous and categorical) variables. The complex temporal dependencies between the variables combined with sparsity of the data makes the event classification problem particularly challengin…
Blog post comparing neural network methods for causal inference.
problem Estimating heterogeneous treatment effects in causal inference.
method Developed and compared a fully connected neural network implementation of Bayesian Causal Forest.
result Improvements in performance in simulation settings.
New deep learning model for matching sets of items, preserving exchangeability.
problem Matching two different sets of items while preserving exchangeability.
method Exchangeable deep neural networks architecture and efficient training framework.
result Significant improvements in fashion set recommendation and group re-identification.
Improved forecasting of investment dynamics across heterogeneous panels using a two-stage model.
problem Forecasting investment dynamics in heterogeneous panels with varying dynamics.
method Two-stage architecture: global pooled AR(1) for shared persistence, local models for residual dynamics.
result Significant improvement in out-of-sample R2 from 0.630 to 0.677, with a gain of 0.047. LATTE tackles heterogeneous network embedding challenges with layer-stacked attention.
problem Aggregating higher-order indirect relations in heterogeneous networks.
method Layer-stacked ATTention Embedding (LATTE) that decomposes meta relations at each layer.
result LATTE achieves state-of-the-art performance on benchmark datasets.
Paper learns a versatile model from diverse networks without annotations.
problem Combining knowledge from different specialized networks without access to their training data.
method Transforms features of diverse networks into a common space and forces a student model to mimic them.
result The student model outperforms individual teacher models on various benchmarks.
Transmeter quickly measures transferability between different datasets.
problem Measuring transferability between heterogeneous multivariate datasets.
method Pre-trained source model, adversarial network, and encoder-decoder architecture.
result Transmeter provides the most accurate transferability measurement up to 10.3 times faster.
Graph attention networks improve performance on heterogeneous graphs.
problem Complex performance of GNNs on heterogeneous graphs.
method Integrating positional encodings into graph attention networks.
result Graph attention networks excel in node classification and link prediction.
A new framework evaluates HTE estimators using relative error.
problem Lack of robust evaluation methods for HTE estimators.
method Proposes a relative error-based evaluation framework and neural network architecture to estimate nuisance parameters and robustly compare HTE estimators.
result Demonstrates reliable comparisons and improved HTE estimation through the proposed framework and learning algorithm.
ChemCPA predicts cellular responses to novel drugs using transfer learning.
problem Scaling high-throughput screens to measure cellular responses for many drugs is costly and challenging.
method ChemCPA, a new encoder-decoder architecture combined with transfer learning.
result Training on existing bulk RNA HTS datasets improves generalization performance, reducing the need for extensive single-cell screens.
Forecaster uses graph Transformers to forecast spatial and time-dependent data.
problem Complex spatial and temporal dependencies in data.
method Graph Transformer architecture with sparsification for spatial and temporal dependencies.
result Forecaster significantly outperforms state-of-the-art baselines in taxi demand forecasting.
ie-HGCN addresses HIN challenges by efficiently learning node representations.
problem Lack of flexibility in exploring meta-paths and high computational complexity in HIN GCN methods.
method Hierarchical aggregation architecture that automatically extracts useful meta-paths and reduces computational cost.
result ie-HGCN outperforms state-of-the-art methods on real network datasets.
daep learns from irregular, multimodal astronomical data.
problem Learning from irregular, multimodal astronomical sequences.
method Diffusion Autoencoder with Perceivers (daep) tokenizes, compresses, and reconstructs data.
result daep outperforms VAE and maep baselines in reconstruction and fine-scale structure preservation.
Transfer learning improves loan recovery rate forecasting under data scarcity.
problem Data scarcity in loan portfolios limits RR modeling accuracy.
method Introduces FT-MDN-Transformer, a mixture-density tabular Transformer architecture for TL.
result FT-MDN-Transformer outperforms baseline models in RR forecasting, especially under covariate and conditional shifts.
MNIST-NET10 fusion improves MNIST classification to 0.1% error rate.
problem Improving MNIST classification accuracy.
method Complex heterogeneous fusion architecture using degree of certainty aggregation.
result MNIST-NET10 achieves 0.1% error rate with 10 misclassifications.
MKL-based models outperform complex multi-omics integrative approaches.
problem Integrating diverse omics data sources.
method Supervised multiple kernel learning with different kernel fusion strategies.
result MKL-based models outperform more complex architectures.
Proposes CoDEAL for estimating heterogeneous treatment effects in panel data models.
problem Estimating heterogeneous treatment effects in causal panel data models with covariate effects.
method Covariate-Adjusted Deep Causal Learning (CoDEAL) integrating neural networks and autoencoders.
result Establishes theoretical guarantees and demonstrates compelling performance in simulations and real data.
Paper develops framework for AI agents in financial markets.
problem Systemic implications of AI in finance depend on agent architectures.
method Four-layer architecture and AFMM model for analysis.
result AI agents can improve market efficiency and resilience.
TiFL divides clients into tiers to improve federated learning performance.
problem Heterogeneity in resource and data quality impacts FL performance.
method TiFL divides clients into tiers based on training performance and selects clients from the same tier in each training round.
result TiFL achieves faster training performance with comparable or better test accuracy.
ISP improves GNN expressivity by stratifying nodes based on graph invariants.
problem Graph Neural Networks struggle with expressivity and structural heterogeneity.
method Invariant-Stratified Propagation (ISP) using ISP-WL and ISPGNN.
result ISP achieves enhanced expressivity beyond 1-WL, with theoretical guarantees and practical improvements.
A meta-learning approach for automatic knowledge transfer between networks.
problem Improving performance in small-data real-world problems with heterogeneous architectures and tasks.
method Meta-learning to automatically learn what knowledge to transfer and where in the target network.
result Meta-transfer approach significantly outperforms hand-crafted methods on various datasets and network architectures.
New GNN method detects money laundering in diverse customer relationships.
problem Insufficient precision and efficiency of current AML systems.
method Heterogeneous Graph Neural Network (GNN) approach.
result Great potential for enhancing electronic surveillance systems for money laundering.
Deep learning method clusters multi-view data matrices.
problem Clustering heterogeneous relational data matrices.
method Deep collective matrix tri-factorization (DCMTF).
result Discover latent clusters across input matrices and their associations.
The rising use of deep learning and other big-data algorithms has led to an increasing demand for hardware platforms that are computationally powerful, yet energy-efficient. Due to the amount of data parallelism in these algorithms, high-performance 3D manycore platforms that incorporate both CPUs and GPUs present a pr…
New federated learning protocols improve on knowledge distillation's poor performance.
problem Designing a universal API for federated learning without public data.
method Proposed Federated Kernel ridge regression using knowledge distillation.
result Performance of new protocols closely matches theoretical predictions.
ModSSC unifies semi-supervised classification for various data types.
problem Fragmented support for semi-supervised classification across different methods, settings, and data types.
method ModSSC is a modular Python framework that supports reproducible and controlled experimentation for semi-supervised classification on heterogeneous data.
result ModSSC enables systematic comparison of semi-supervised learning across various datasets and model backbones.
Researchers analyze and compare nonparametric meta-learners for estimating heterogeneous treatment effects.
problem Evaluating treatment effectiveness in empirical science, especially when effects vary among individuals.
method Theoretical analysis of four meta-learning strategies, focusing on plug-in estimation and pseudo-outcome regression.
result Theoretical insights guide algorithm design and reveal relative strengths of different learners under various data-generating processes.
There are many real-world knowledge based networked systems with multi-type interacting entities that can be regarded as heterogeneous networks including human connections and biological evolutions. One of the main issues in such networks is to predict information diffusion such as shape, growth and size of social even…
AMF-VI uses adaptive mixtures of flows for robust VI across diverse distributions.
problem Inconsistent behavior of single-flow models across different distributions.
method Sequential expert training of individual flows and adaptive global weight estimation via likelihood-driven updates.
result AMF-VI achieves lower negative log-likelihood and stable gains in transport metrics across various posterior families.
Intelligent transportation systems (ITSs) will be a major component of tomorrow's smart cities. However, realizing the true potential of ITSs requires ultra-low latency and reliable data analytics solutions that can combine, in real-time, a heterogeneous mix of data stemming from the ITS network and its environment. Su…
PANIS learns PDE surrogates for heterogeneous materials without solving the PDE.
problem Learning surrogates for parametrized PDEs in heterogeneous media.
method Physics-aware neural implicit solvers combining probabilistic learning and physics-informed discretization.
result Learned surrogates for effective solutions in heterogeneous materials without solving the reference problem.
DAG-FM discovers causal relationships from heterogeneous data.
problem Challenges in causal discovery from heterogeneous causal mechanisms.
method DAG-FM uses two specialized Transformer-based sub-modules and a robust tabular interaction block to model complex row-column interactions.
result DAG-FM achieves state-of-the-art performance on synthetic and real-world datasets.
Adapts LRP for LSTM to explain sequential data.
problem Lack of explainable AI for LSTM models.
method Extends LRP to LSTM, introduces new propagation scheme.
result Delivers faithful explanations for LSTM predictions.
HeteGCN improves text classification with efficient, scalable graph models.
problem Text classification with large datasets and features, especially in small labeled sets.
method HeteGCN combines PTE and TextGCN, using heterogeneous graphs and feature embeddings.
result HeteGCN achieves better performance and scalability compared to existing methods.
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.
SPADE-S improves time series forecasting accuracy for low-magnitude and sparse data.
problem Challenges in forecasting time series with strong heterogeneity in magnitude and sparsity.
method SPADE-S is a robust forecasting architecture that reduces biases and improves overall prediction accuracy.
result SPADE-S outperforms existing state-of-the-art approaches across diverse use cases, improving forecast accuracy by up to 15%.
Inspired by the importance of diversity in biological system, we built an heterogeneous system that could achieve this goal. Our architecture could be summarized in two basic steps. First, we generate a diverse set of classification hypothesis using both Convolutional Neural Networks, currently the state-of-the-art tec…
New algorithm resists Byzantine attacks in distributed SGD for heterogeneous data.
problem Byzantine attacks in distributed SGD for heterogeneous data.
method Polynomial-time outlier-filtering for robust mean estimation, new matrix concentration result.
result Tolerates up to 25% Byzantine workers and achieves optimal convergence rates.
A new clustering model for mixed datasets combines continuous and non-continuous data.
problem Challenges in clustering mixed data due to heterogeneous variables.
method Mixed Deep Gaussian Mixture Model (MDGMM) with multilayer architecture.
result Automatic selection of model specifications and optimal number of clusters.
Self-supervised pretraining for heterogeneous hypergraphs improves graph-based tasks.
problem Capturing higher-order relations in heterogeneous hypergraphs.
method SPHH framework for self-supervised pretraining of heterogeneous HyperGNNs.
result SPHH consistently outperforms state-of-the-art baselines in various downstream tasks.
AEGCN uses autoencoder constraints to improve graph node classification.
problem Node classification on graph domains with reduced information loss.
method Autoencoder-constrained graph convolutional network (AEGCN).
result Adding autoencoder constraints significantly improves graph convolutional network performance.
Forecasting based on financial time-series is a challenging task since most real-world data exhibits nonstationary property and nonlinear dependencies. In addition, different data modalities often embed different nonlinear relationships which are difficult to capture by human-designed models. To tackle the supervised l…