Method detects competitive inhibitory activity between compounds and proteins using tensor factorization.
problem Understanding the type of inhibitory interaction in drug design.
method Proposes Macau tensor factorization method to combine different measurement types into a single tensor.
result Can identify latent subspace separating IC50 and Ki measurements.
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.
Inspired by LSTMs, a new neural network model mimics cortical microcircuits.
problem Understanding the computational principles of cortical microcircuits.
method Introducing a gated-recurrent neural network (subLSTM) based on inhibitory cells.
result SubLSTM units achieve similar performance to LSTM units in sequential tasks.
Exact asymptotic solutions found for nonlinear Hawkes processes.
problem Analytical solutions for nonlinear Hawkes processes with positive and negative feedbacks.
method Field master equation approach to classify steady-state solutions.
result Explicit power law formulas for steady-state intensity distributions Pss(λ)∝λ−1−a, with a as a function of parameters. Novel approach constructs differential causal networks from EEG data.
problem Difficulty in modeling interactions of thousands of neurons in group comparisons.
method Hierarchical differential dynamic causal nets based on Chen-Fliess expansions.
result Evidence of network functional disruptions in epileptic brains.
LM-SNNs use lattice maps to classify and cluster images.
problem Image classification and clustering.
method Lattice map spiking neural networks with cooperative and competitive interactions, inhibition strategies, and biologically motivated learning rules.
result LM-SNNs effectively classify and cluster images using self-organized filters.
New approach models brain dynamics using coupled van der Pol oscillators and LSTM.
problem Capturing nonlinear dynamics in brain calcium imaging data.
method Proposes a new approach combining van der Pol oscillators and LSTM for modeling brain activity.
result Shows improved accuracy and interpretability compared to LSTM and hybrid VDP-LSTM approach.
Study uses Hawkes processes to analyze stock market contagion in China.
problem Understanding contagion in Chinese stock market.
method Fitting Hawkes processes to daily returns and sector indices.
result Identifies long-term dependencies and trending patterns in sector indices.
Proposes a method to explain deep neural networks by identifying representer points in the training set.
problem Explaining the predictions of deep neural networks.
method Identifying representer points in the training set to decompose neural network predictions.
result Provides a deeper understanding of neural network predictions through positive and negative representer values.
Theory reconstructs network connectivity from event timings.
problem Reconstructing network connectivity from incomplete continuous-time data.
method Linearizes event space mapping to reveal direct influences.
result Reveals synapse presence and inhibitory/activating nature.
Flexible Hawkes model with Gaussian process self-effects for time-dependent data.
problem Modeling time-dependent point processes with history dependence and self-effects.
method Extended Hawkes process with Gaussian process self-effects for both excitatory and inhibitory types, using Bayesian inference and mean-field variational approximation.
result Efficient approximate Bayesian inference achieved via data augmentation and mean-field variational approach.
Estimates neuronal connectivity from spike times using flexible Hawkes processes.
problem Learning latent network structure from multivariate point process data.
method Proposes a new nonstationary Hawkes process and uses sparse least squares estimation.
result Establishes non-asymptotic error bounds and selection consistency for estimated parameters.
Unified framework trains spiking neural networks for various cognitive tasks.
problem Limitations of conventional neural network models in matching experimental neural dynamics.
method Modified SpikeProp learning algorithm, including biological features.
result Framework successfully trained spiking neural networks for diverse cognitive tasks.
A novel Hawkes Process model captures order sizes in LOBs, improving fit quality and market impact studies.
problem Capturing the variability in order sizes in Limit Order Books (LOBs).
method Compound Hawkes Process with time-varying parameters and non-parametric calibration.
result Improved fit quality and empirical market impact function replication.
Balanced excitation and inhibition enhance neuronal selectivity and robustness.
problem Ensuring robust neuronal responses in noisy environments.
method Investigated the conditions for balanced excitation and inhibition to enhance robustness of single neurons and network attractor states.
result Balanced excitation and inhibition are crucial for high-capacity, noise-resistant neuronal selectivity.
SNNs enhance high-frequency price spike forecasting in HFT environments.
problem Conventional financial models fail to capture fine temporal structure in high-frequency price spikes.
method Application of Spiking Neural Networks (SNNs) with hyperparameter tuning via Bayesian Optimization (BO).
result SNN models optimized with PSA achieve significantly higher cumulative returns in backtesting.
A novel algorithm optimizes sparsity in reservoir computing inspired by insect brain.
problem Optimizing sparsity in reservoir computing networks.
method Inspired by insect brain, the algorithm optimizes sparsity levels by adjusting node firing thresholds.
result The algorithm outperforms standard gradient descent on tasks involving better classification, memorization, and convergence.
RECON reconstructs regulatory networks from time-course data, reducing spurious edges and preserving true regulatory edges.
problem Reconstructing regulatory networks from time-course data with minimal spurious edges and preserving true regulatory relationships.
method RECON uses an integral-based additive nonparametric ODE model with five methodological advances to reconstruct regulatory networks.
result RECON consistently outperforms existing methods, reducing spurious edges and preserving true regulatory edges across various scenarios.
Generative model tailors anticancer drugs based on transcriptomic data.
problem Designing effective anticancer drugs considering genetic profiles.
method RL framework using pretrained VAEs to generate compounds conditioned on transcriptomic data.
result Generative model produces molecules with high predicted inhibitory effects.
A new model uses 'ghost units' to enable efficient backpropagation in deep neural networks.
problem How to achieve efficient backpropagation in deep neural networks with biological plausibility.
method Introduces 'ghost units' to cancel feedback, enabling efficient error backpropagation.
result Demonstrates that the model can approximate error gradients and achieve good performance on classification tasks.
IFM improves recommender systems by learning flexible feature interactions.
problem Dealing with feature interactions in recommender systems can degrade performance.
method Introduces Interaction-Aware Mechanism (IAM) to learn feature and field interactions.
result Improves performance on two well-known datasets compared to state-of-the-art methods.
Surrogate-based analysis of interactions via local effect smooths
problem Detecting and characterizing feature interactions in machine learning models
method Surrogate-based analysis using generalized additive models
result Empirical validation of effectiveness for pairwise interactions
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.
Theory of learning with weight-distribution constraints.
problem Understanding how structure influences function in neural networks.
method Statistical mechanical theory and optimal transport.
result Reduction in capacity due to constrained weight-distribution is related to Wasserstein distance.
Interactive learning framework for various settings.
problem Various interactive learning settings.
method Adapted active learning algorithm for interactive structure discovery.
result Noise-tolerant algorithm with favorable query complexity.
A new method for identifying interactions in high dimensions.
problem Challenges in identifying interactions with many covariates.
method Interaction pursuit (IP) procedure: feature screening and selection.
result The method screens interactions separately from main effects, improving effectiveness.
InteractE improves link prediction in KGs by increasing feature interactions.
problem Improving link prediction in knowledge graphs by inferring missing links.
method Feature permutation, novel feature reshaping, circular convolution.
result InteractE outperforms ConvE on multiple KG datasets.
Enhances MTGP for better hierarchical latent interactions.
problem Current MTGPs struggle with hierarchical latent interactions.
method Proposes a novel kernel representation for hierarchical interactions in LMC of MTGP.
result Promotes knowledge transferring in MTGP through hierarchical interactions.
iKF method uncovers complex variable interactions for scientific discovery.
problem Limited interpretability of existing models in decision-making applications.
method Iterative Kings' Forests (iKF) method to uncover multi-order interactions.
result iKF provides strong interpretive power for explainable modeling.
Graph neural network predicts vehicle interactions and trajectories for autonomous driving.
problem Predicting future motion of vehicles in traffic scenes.
method Graph neural network that jointly predicts interaction modes and 5-second future trajectories.
result Jointly predicting trajectories and interaction modes leads to lower trajectory error.
Detects interactions in neural network weights for better interpretation.
problem Interpreting neural networks for understanding interactions.
method Directly interprets neural network weights to detect interactions.
result Significantly better or similar interaction detection compared to state-of-the-art.
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.
We describe and extract time-ordered multibody interactions from complex systems.
problem Complex systems with temporal and multibody dependencies.
method Decompose multivariate Markov chains into time-ordered multibody interactions. Algorithm to extract interactions from data. Measure complexity of interaction ensembles.
result Robust and efficient algorithm to infer time-ordered multibody interactions from data.
Robot learns to interact naturally with humans through neural attention.
problem Developing a robot that can respond to complex human behaviors in a natural way.
method Multimodal Deep Attention Recurrent Q-Network trained using reinforcement learning.
result The robot learned to respond to human behaviors in a perceivable and socially acceptable manner.
Dropout regularizes against high-order interactions by canceling interaction rates.
problem Overfitting to high-order interactions in neural networks.
method Analyzes Dropout through the lens of interaction effects, showing how it effectively cancels out the probability of surviving interactions of different orders.
result Dropout regularizes against high-order interactions by effectively canceling out the probability of surviving interactions of different orders.
SocialInteractionGAN generates realistic human interactions from low-dimensional data.
problem Generating realistic human interactions from limited data.
method Adversarial architecture with a recurrent encoder-decoder generator and dual-stream discriminator.
result SocialInteractionGAN produces high-quality action sequences of interacting people.
A new method detects interactions in machine learning models.
problem Interpreting non-linear and interaction effects in machine learning models.
method Regional effect plots with implicit interaction detection.
result The method quantifies and interprets feature effects reliably, less confounded by interactions.
Robot learns to imitate human interactions through deep learning.
problem Teaching robots to coordinate actions with human partners.
method Deep learning framework for motion embedding, prediction, and trajectory generation.
result Importance of predictive and adaptive components for successful imitation.
xDeepInt learns both vector-wise and bit-wise feature interactions.
problem Learning feature interactions for CTR prediction and recommendation.
method Polynomial Interaction Network (PIN) architecture with subspace-crossing mechanism.
result xDeepInt outperforms state-of-the-art models in CTR prediction and recommendation.
Bayesian neural networks detect complex interactions with uncertainty.
problem Estimating global pairwise interaction effects with uncertainty.
method Bayesian neural network for modeling interactions, GEH for estimating interaction effects.
result The method empirically outperforms alternatives and detects interpretable interactions.
This paper explores how interactive protocols enhance local differential privacy.
problem The power of interactive protocols in local differential privacy.
method Classification of locally private protocols by compositionality and transformation of fully interactive protocols into sequentially interactive ones.
result Fully interactive protocols can solve problems that sequentially interactive protocols cannot without a significant increase in sample complexity.
Mahé provides hierarchical explanations for complex interactions in machine learning models.
problem Capturing and explaining complex interactions in machine learning models.
method Model-agnostic hierarchical explanations through local interpretation and context-free generalization.
result Improved local interaction interpretations and successful explanation of context-free interactions.
Agent learns object segmentation through self-supervised interactions.
problem Object segmentation in visual observations.
method Self-supervised learning through interaction, robust set loss.
result Model generalizes to novel objects and backgrounds.
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.
Paper introduces IC-index to evaluate interaction prediction methods.
problem Evaluate interaction prediction methods using IC-index.
method IC-index measures interaction direction prediction performance.
result IC-index complements existing prediction performance estimators.
This paper uses Gaussian mixtures to mimic interactions in large language models.
problem Simulating interactions in large language models (LLMs) is computationally expensive.
method Developed an interacting Gaussian mixture model (GMM) system to mimic LLM interactions.
result The interacting Gaussian mixture model system can generate, exchange, and update data and parameters efficiently.
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.
Automated tests detect interactions in unstructured data.
problem Detecting interactions between latent variables in low-dimensional systems.
method Derive two interaction tests based on pairwise interventions and integrate them into an active learning pipeline.
result Tests can identify more known biological interactions than random search and standard active learning baselines.