A new method detects interactions in neural networks using topological analysis.
problem Detecting interactions between input features in neural networks.
method Topological analysis of neural network connectivity to quantify interaction strength.
result The PID algorithm outperforms state-of-the-art baselines in interaction detection tasks.
PIN models feature interactions using a neural network that mimics decision trees.
problem Modeling feature interactions in tabular data for predictive modeling.
method Tree-like Pairwise Interaction Network (PIN) architecture that captures pairwise feature interactions through a shared feed-forward neural network.
result PIN outperforms traditional and modern neural networks benchmarks in predictive accuracy.
Paper proposes FINN for better CTR prediction by modeling feature interactions.
problem Improving CTR prediction in advertising and recommendation systems.
method Proposes Feature Interaction based Neural Network (FINN) to model feature interactions.
result FINN outperforms other deep models in CTR prediction tasks.
Interpreting neural networks is a crucial and challenging task in machine learning. In this paper, we develop a novel framework for detecting statistical interactions captured by a feedforward multilayer neural network by directly interpreting its learned weights. Depending on the desired interactions, our method can a…
Automates finding interactions in GLMs using neural networks.
problem Time-consuming and expert-dependent search for GLM interactions.
method Neural networks and model-specific interaction detection method.
result Computational speed improvement over traditional methods.
A graph neural network detects beneficial feature interactions for recommender systems.
problem Feature interactions are crucial but not all are beneficial for recommendation accuracy.
method Graph neural network with L0 activation regularization for edge prediction.
result The model outperforms baselines and automatically identifies beneficial feature interactions.
This work uses decision trees to encode relevant features and their interactions into neural networks, improving model performance.
problem Overfitting in neural networks with many irrelevant variables.
method Defines a mapping to encode decision tree extracted relationships into a neural network.
result The approach outperforms fully connected neural networks and tree-based methods.
Deep model learns protein interfaces from high-order interactions.
problem Predicting protein interfaces from amino acid pairs.
method Graph neural networks and convolutional neural networks for 2D dense predictions.
result Our method consistently improves interface prediction performance.
New method explains feature interactions in neural networks.
problem Understanding feature interactions in deep networks.
method Integrated Hessians, an extension of Integrated Gradients.
result Integrated Hessians explains pairwise feature interactions efficiently and accurately.
MFNs parameterize non-local interactions through matrix equivariant functions, improving graph neural network performance.
problem Challenges in modeling non-local interactions in graphs, such as oversmoothing and oversquashing.
method Matrix Function Neural Networks (MFNs) using resolvent expansions for non-local interactions.
result Achieves state-of-the-art performance in graph benchmarks and captures intricate non-local interactions.
Interactive framework improves understanding of deep neural networks.
problem False sense of comprehension from static explanation methods.
method Interactive framework allowing exhaustive inspection and testing of decisions.
result Interactive approach leads to better understanding of complex decision boundaries.
Simplicial neural networks extend graph neural networks to handle higher-order interactions.
problem Handling higher-order interactions in complex data structures.
method Define a convolution operation for simplicial complexes and use it to construct convolutional neural networks.
result SNNs effectively impute missing data in coauthorship complexes.
SIAN bridges simple models to neural networks by identifying necessary feature combinations.
problem The gap between simple models and powerful neural networks in performance.
method Feature interaction detection and sparse selection algorithm.
result Competitive performance across multiple tabular datasets with optimal tradeoff.
Estimating global pairwise interaction effects, i.e., the difference between the joint effect and the sum of marginal effects of two input features, with uncertainty properly quantified, is centrally important in science applications. We propose a non-parametric probabilistic method for detecting interaction effects of…
Study reveals self-attention's role in learning and generalizing interactions.
problem Understanding self-attention's theoretical role in neural architectures.
method Interacting entities analysis, including multi-agent RL and genetic sequences.
result Self-attention efficiently represents, learns, and generalizes pairwise interactions.
GAMI-Net improves neural network interpretability while maintaining accuracy.
problem Lack of interpretability in neural network models.
method GAMI-Net is a disentangled feedforward network with multiple additive subnetworks designed for capturing main effects and pairwise interactions, considering sparsity, heredity, and marginal clarity.
result GAMI-Net achieves superior interpretability and competitive prediction accuracy compared to explainable boosting machine and other models.
The paper explains DNNs by quantifying interactions among input variables.
problem Understanding and explaining the complex behavior of deep neural networks.
method The paper defines and quantifies the significance of interactions among multiple input variables using the Shapley value.
result The proposed method effectively explains the behavior of DNNs by assigning attribution values to input variables.
In this work, we aim to predict the future motion of vehicles in a traffic scene by explicitly modeling their pairwise interactions. Specifically, we propose a graph neural network that jointly predicts the discrete interaction modes and 5-second future trajectories for all agents in the scene. Our model infers an inte…
By interpreting a traffic scene as a graph of interacting vehicles, we gain a flexible abstract representation which allows us to apply Graph Neural Network (GNN) models for traffic prediction. These naturally take interaction between traffic participants into account while being computationally efficient and providing…
Paper improves neural interaction modeling using nonlinear Hawkes processes.
problem Inability of classic Hawkes process to model inhibitory interactions.
method Augmented auxiliary latent variables and EM algorithm for efficient inference.
result Demonstrates accurate and efficient estimation of neural interaction dynamics.
InteractionNet models noncovalent protein-ligand interactions with GNNs and explains predictions.
problem Modeling noncovalent protein-ligand interactions with graph neural networks.
method InteractionNet uses a GNN architecture with separated covalent and noncovalent convolution layers and layer-wise relevance propagation for explainability.
result InteractionNet successfully predicts noncovalent protein-ligand interactions with chemical relevance.
The paper improves dropout's utility by reducing interactions in deep neural networks.
problem Over-fitting problem in deep learning.
method Game-theoretic interactions analysis and interaction loss.
result Interaction loss improves dropout's utility and boosts DNN performance.
In this study, we analyzed the activity of monkey V1 neurons responding to grating stimuli of different orientations using inference methods for a time-dependent Ising model. The method provides optimal estimation of time-dependent neural interactions with credible intervals according to the sequential Bayes estimation…
Archipelago provides interpretable explanations of feature interactions in machine learning models.
problem Interpreting the impact of feature interactions on predictions in machine learning models.
method Archipelago is a novel framework for extracting and attributing feature interactions in a scalable and interpretable manner.
result Archipelago provides significantly more interpretable explanations of feature interactions than comparable methods.
Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics. The interplay of components can give rise to complex behavior, which can often be explained using a simple model of the system's constituent parts. In this work, we introduce the neural relational inference (NRI…
A new graph model HMG and neural network HMGNN improve molecule property predictions.
problem Predicting quantum mechanical properties of molecules with limited consideration of many-body interactions.
method Introducing heterogeneous molecular graphs (HMG) and building HMGNN on neural message passing scheme.
result HMGNN achieves state-of-the-art performance in 9 out of 12 tasks on the QM9 dataset.
SLIM model tackles graph classification by resolving part-interaction dilemmas.
problem Difficulty in modeling graph parts and their interactions in graph classification.
method SLIM model, which solves resolution dilemmas and leverages explicit interactions.
result SLIM offers improved interpretability, accuracy, and new insights in graph representation learning.
CREIMBO models diverse brain activity by identifying hidden neural sub-circuits and their non-stationary interactions.
problem Lack of alignment in neural recordings limits analysis of brain-wide dynamics.
method CREIMBO learns a unified model of neural dynamics by assuming multiple hidden global sub-circuits representing ensemble interactions.
result CREIMBO discovers session-specific neural ensembles and their non-stationary interactions, revealing cross-subject neural mechanisms.
Graphs can model interactions between vertices, but how well depends on graph structure.
problem Lack of formal characterization of GNNs' ability to model interactions between vertices.
method Formalized interaction strength using separation rank and quantified it for different partitions of vertices.
result GNNs' ability to model interactions is primarily determined by the partition's walk index.
Neural interaction discoveries can be real or artifacts of model flexibility.
problem Identifying real neural interactions from data.
method Using a multiplicative-gating extension of neural additive vector autoregression.
result Effective rank of the joint lag-block covariance predicts interaction recoverability.
Ensembles of neural networks learn better by sharing information.
problem Improving performance of neural networks through collective learning.
method Modeling neural networks as socially interacting agents aiming to maximize their own performance and functional relations to others.
result Optimal collective performance emerges from local interactions between networks, leading to specialization and higher confidence.
Inspired by the immense success of deep learning, graph neural networks (GNNs) are widely used to learn powerful node representations and have demonstrated promising performance on different graph learning tasks. However, most real-world graphs often come with high-dimensional and sparse node features, rendering the le…
This study explores how feature graphs enhance GNNs' performance in modeling interactions.
problem Improving GNNs' ability to model feature interactions effectively.
method Investigates feature graphs and their importance in GNNs, using experiments and theoretical support.
result Edges between interacting features are crucial for GNNs, while non-interaction edges can degrade performance.
Predicts student performance in interactive online question pools using GNNs.
problem Predicting student performance in interactive online question pools with evolving knowledge.
method Proposes R^2GCN, a GNN model for heterogeneous networks to predict student performance.
result Achieves higher accuracy in student performance prediction than traditional methods.
This work discovers latent field effects governing interacting dynamical systems.
problem Discovering field effects governing interacting dynamical systems.
method Proposes neural fields to learn latent force fields from observed dynamics, disentangling local object interactions and global field effects.
result Accurately discovers latent field effects in various dynamical systems.
The paper models user-advertiser interactions using point processes.
problem Causal inference problems in user-advertiser interaction.
method Temporal marked point processes and neural point processes.
result Neural point processes as practical solutions.
STNN-DDI predicts drug interactions using substructure-aware neural networks.
problem Predicting drug-drug interactions (DDIs) to avoid side effects in poly-drug treatments.
method Designing a novel Substructure-ware Tensor Neural Network (STNN-DDI) that learns a 3-D tensor of substructure-substructure interactions.
result Significant improvement in AUC, AUPR, Accuracy, and Precision compared to state-of-the-art models.
IAL uses interactive learning to improve model performance with minimal human feedback.
problem Overfitting and high human interaction cost in training neural networks.
method IAL framework with NAP attention generator and reranking algorithm.
result IAL significantly outperforms baselines with less retraining and human interaction.
New principle reveals how neural networks learn complex interactions.
problem Understanding neural networks' success and complexity.
method Infinite-width networks, focusing on frequency and space.
result Fine-grained eigenstructure improves network learnability.
A new method captures higher-order interactions in data clusters.
problem Accurately characterizing complex higher-order variable interactions.
method Local Correlation Explanation (CorEx) method: clustering and total correlation.
result Captures higher-order interactions at a local scale.
Bayesian principles improve neural additive models for better feature selection and uncertainty.
problem Lack of calibrated uncertainties and feature selection in neural additive models.
method Augmenting NAMs with Bayesian principles to provide credible intervals, feature selection, and interaction ranking.
result Improved performance on tabular datasets and real-world medical tasks.
Estimates mean dimension of neural networks to reveal interaction effects.
problem Understanding interaction effects in neural networks.
method Estimation procedure for mean dimension from datasets, analyzing layer-by-layer evolution and impact of activation functions.
result Mean dimension reveals differences in interaction magnitude across neural network architectures.
Bi-GNN models drug interactions using a bi-level graph approach.
problem Predicting drug-drug interactions using machine learning.
method Bi-level graph neural networks that consider both interaction graph and representation graphs of drugs.
result Bi-GNN model improves DDI prediction accuracy compared to existing methods.
New method improves graph neural networks by considering different types of relations in sampling.
problem Current graph neural networks ignore relation types in biomedical graphs, leading to suboptimal performance.
method Proposes relation-dependent sampling for multi-relational graphs to balance relation frequency and importance.
result State-of-the-art graph neural networks achieve better accuracy and efficiency with relation-dependent sampling.
HGNet improves GNNs' ability to handle long-range interactions in graphs.
problem Insufficiency of GNNs in capturing long-range interactions.
method Introduces hierarchical message passing models with multi-resolution graph representations.
result HGNet outperforms conventional GNNs in molecular property prediction.
A new graph neural network framework captures long-range interactions efficiently.
problem Efficiently modeling long-range interactions in graph neural networks for PDEs.
method Proposes a multi-level graph neural network framework using multipole methods.
result Captures interaction at all ranges with only linear complexity, learning discretization-invariant solution operators.
DeepLight accelerates CTR predictions in ad serving by 46X.
problem Significantly increased serving delay and high memory usage for ad serving.
method Explicitly searching feature interactions, pruning layers, promoting sparsity.
result Accelerates model inference by 46X on Criteo dataset.
CBNNs model survival with time-varying interactions, outperforming other methods.
problem Complex covariate effects and time-varying interactions in survival analysis.
method Combines case-base sampling with neural networks to model time-varying effects and complex baseline hazards.
result CBNNs outperform regression and neural network-based survival methods in simulations and real data applications.