Deep models learn interactions across sets, achieving state-of-the-art performance.
problem Modeling interactions across multiple sets of objects.
method Permutation-equivariant parameter-sharing scheme for deep learning.
result State-of-the-art performance on matrix completion benchmarks and extrapolation tasks.
BayReL learns molecular interactions across multi-omics data.
problem Inferring meaningful interactions across diverse molecular data types.
method BayReL uses Bayesian representation learning with graph models to integrate multi-omics data.
result BayReL outperforms existing methods in inferring molecular interactions.
Gaussian process framework learns interaction kernels in multi-species particle systems.
problem Learning interaction kernels in multi-species interacting particle systems from trajectory data.
method Nonparametric Bayesian approach with Gaussian processes.
result Established rigorous statistical guarantees for recoverability and optimality of interaction kernels.
Proposes online learning for Hawkes processes with network structure and event interaction.
problem Modeling complex interactions and latent structures in network events.
method Online learning approach for mixture of multivariate Hawkes processes.
result Efficacy demonstrated on synthetic and real-world data.
Interactive machine learning improves learning efficiency with user input.
problem Expensive, time-consuming, or risky acquisition of labeled data and decision-making.
method Develops new algorithms for active learning, sequential decision making, and model selection under partial feedback.
result First efficient algorithms achieving exponential label savings and independent of action space size.
The paper proposes a method to transfer knowledge across different settings using causal theory.
problem Learning transfer across similar but different settings.
method Bayesian perspective of causal theory induction, integrating instance-level associative learning and abstract-level structural causal knowledge.
result The proposed model achieved transfer behavior across trials and learning situations, unlike RL algorithms.
FLDCRF improves sequence labeling performance with latent dynamics interactions.
problem Sequence labeling with improved performance and latent dynamics interactions.
method Factored Latent-Dynamic Conditional Random Fields (FLDCRF) with multiple latent dynamics interactions.
result FLDCRF outperforms state-of-the-art models across multiple datasets.
Study identifies unique minimizers for interaction kernels in particle systems.
problem Identifying unique interaction kernels in mean-field equations of interacting particles.
method Data-adaptive L2 spaces, RKHS analysis, regularization. result Characterization of identifiability in both finite and infinite particle systems.
HyperSHAP explains HPO hyperparameters and interactions, improving trust and adoption.
problem Tackling opaque HPO methods and lack of user trust.
method Game-theoretic explainability framework based on Shapley values and interactions.
result Provides insights into hyperparameter contributions and interactions.
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.
A new method for finding efficient neural interaction functions in collaborative filtering.
problem Finding consistent good performance for complex interactions in collaborative filtering.
method Proposes a search algorithm for simple neural interaction functions (SIF) in CF, using a structured multi-layer perceptron.
result Demonstrates much better prediction performance and distinct IFCs for different data sets and tasks.
Unified approach detects traffic conflicts across various interactions.
problem Inconsistent detection of traffic conflicts across different interactions.
method Unified probabilistic approach decomposes conflicts into statistical learning tasks.
result Effective collision warnings across diverse datasets and environments.
Interactive tool helps understand ML model performance.
problem Understanding ML model performance across various inputs.
method Open-source What-If Tool for interactive probing and analysis.
result Allows testing performance in hypothetical situations and measuring fairness.
New approach improves cross-domain recommendation for sparse target domains.
problem Cross-domain recommendation challenges with sparse target domains.
method Guided neural collaborative filtering with domain-invariant components across dense and sparse domains.
result Effective and scalable approach demonstrated on public and Visa datasets.
Study higher-order interactions in networks, proposing link prediction as a new benchmark.
problem Understanding higher-order interactions in complex systems.
method Temporal analysis of 19 datasets, focusing on interactions involving more than two nodes.
result Higher-order interactions are consistent across different systems, with tie strength and edge density influencing their presence.
New kernels capture both local and non-local interactions efficiently.
problem Designing kernels that capture both local and non-local interactions while remaining computationally tractable.
method Spectral truncation kernels based on C∗-algebra. result Spectral truncation kernels induce interactions across the data function domain and reduce computational cost.
BaGGLS models biological interactions using Bayesian shrinkage for interpretability.
problem Interpreting complex interactions in high-dimensional biological data.
method Bayesian group global-local shrinkage prior with variational approximation.
result BaGGLS outperforms other methods in interaction detection and scalability.
ISAAC audits deep models for drug-target interactions, revealing structural differences.
problem Deep models for DTI often use irrelevant features, making them hard to evaluate.
method ISAAC uses intervention-based structural auditing to evaluate model sensitivity.
result ISAAC reveals significant structural differences in DTI models' reasoning.
SkewSize detects model biases by analyzing mistakes across subgroups.
problem Benchmarking model performance in the presence of spurious correlations.
method Introducing SkewSize, a metric that captures bias from model mistakes.
result SkewSize highlights biases not captured by other metrics.
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.
Improved drug-protein interaction prediction using FTL method.
problem Predicting drug-protein interactions from noisy data with uncertain labels.
method Filtered Transfer Learning (FTL) method that fine-tunes a deep neural network across multiple tiers of data confidence.
result FTL method outperforms deep neural networks trained on single confidence ranges.
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.
SurvFD and SurvSHAP-IQ provide interpretable survival models by analyzing feature interactions.
problem Non-additivity of hazard and survival functions limits standard additive explanation methods.
method SurvFD decomposes higher-order effects into time-dependent and time-independent components, extending Shapley interactions to time-indexed functions.
result SurvFD and SurvSHAP-IQ offer a new perspective on survival explanations, explicitly characterizing feature 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.
MIDAS learns to adaptively control other cars in urban driving scenarios.
problem Autonomous vehicles need to interact with other agents on the road.
method Reinforcement learning with attention mechanism to handle multiple agents.
result MIDAS policies are adaptive and robust to external changes.
A game-theoretic framework identifies influential hyperparameters for neural networks.
problem Understanding which hyperparameters are most important for neural network performance.
method Employing Shapley Effects for global sensitivity analysis and Pareto front sets for identifying effective configurations.
result Reveals which hyperparameters are most influential for different objectives in neural networks.
Bayesian model predicts phenotype effects from multi-environmental factors.
problem Predict phenotype effects from multi-environmental trials.
method Bayesian tensor regression with spike-and-slab structure.
result Model outperforms previous methods in simulation and real-world data.
Model predicts user engagement and survival time in games.
problem Building data-efficient engagement models for diverse games.
method Data-driven approach using minimal metrics.
result Joint estimates of survival time and churn probability.
SPINEX improves clustering with explainable neighbors, outperforming other methods.
problem Improving clustering performance and explainability.
method Leverages similarity and higher-order interactions for clustering.
result SPINEX outperforms 13 clustering algorithms across various datasets.
Automates RL with sample-efficient hyperparameter optimization.
problem Challenges in applying deep RL due to hyperparameter sensitivity and inefficiency.
method Population-based AutoRL framework for meta-optimizing RL algorithms and architectures.
result Reduces the number of environment interactions needed for meta-optimization by up to an order of magnitude.
A new model CDT improves cross-domain recommendation by learning translation vectors.
problem Improving cross-domain recommendation by transferring user preferences across different platforms.
method Translation-based learning approach with embedding space and factorization machines.
result The proposed CDT model outperforms other cross-domain strategies in six publicly available tasks.
ReOPD uses pre-collected teacher trajectories to distill knowledge from multi-turn interactions.
problem The cost of fully online on-policy distillation for multi-turn interactions.
method ReOPD, an off-environment alternative that reuses pre-collected teacher trajectories as replayed prefixes, addressing the prefix trap and distribution shift.
result ReOPD preserves or improves OPD-level accuracy, uses zero tool calls, and is at least 4imes faster per training step. Proposes guided networks for fast, accurate few-shot segmentation.
problem Few supervision limits learning-based segmentation methods.
method Extracts latent task representation from supervision, optimizes end-to-end.
result First results for segmentation from one pixel per concept, real-time interactive video segmentation.
New method estimates treatment effects in complex interference settings.
problem Challenges in estimating treatment effects due to unknown interference.
method Higher-order causal message passing for non-linear feature learning.
result Effective estimation of treatment effect dynamics in complex interference.
A two-stream reinforcement learning model improves decision-making across human and neuropsychiatric studies.
problem Improving reinforcement learning models to better simulate human decision-making and neuropsychiatric conditions.
method Proposes a two-stream reinforcement learning model that processes positive and negative rewards and incorporates reward-processing biases.
result The two-stream model outperforms standard Q-learning and SARSA methods on various tasks and datasets.
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.
Quaternion self-attention reduces computational cost and improves performance.
problem Existing quaternion self-attention increases computational cost and diverges attention distributions.
method Proposes a shared-score quaternion self-attention mechanism.
result Reduces score-computation multiplications by 75% and softmax operations from four to one.
Bayesian method selects interacting regions in Markov models.
problem Estimating interacting regions in Markov Random Fields.
method Reversible Jump Monte Carlo Markov Chain algorithm with pseudoposteriors.
result Proposed method accurately selects interacting regions in simulations and real data.
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.
Federated Granger causality learns reliable interactions without sharing data.
problem Uncertainty in federated Granger causality estimates.
method Closed-form covariance recursions and spectral-radius-based convergence conditions.
result Uncertainty depends only on client data statistics and is independent of model parameters.
Framework for joint inference of network topology and interaction types in heterogeneous systems.
problem Joint inference of network topology, multi-type interaction kernels, and latent type assignments in heterogeneous interacting particle systems.
method Three-stage approach: shared structure recovery, discrete interaction type identification, and matrix factorization.
result The method yields accurate reconstruction of underlying dynamics and is robust to noise.
New method uncovers global topology through local interactions, reducing algorithm complexity.
problem Global interaction is necessary for forming feature maps that preserve global topology.
method Competing agents engage in local interactions to form feature maps without global interaction.
result Local interactions can uncover global topology, leading to consistent map quality across diverse datasets.
NCoRE learns counterfactual representations for combined treatments.
problem Estimating individual response to multiple simultaneous interventions.
method Neural conditional representation with modulators for cross-treatment interactions.
result NCoRE significantly outperforms existing methods in counterfactual treatment effect estimation.
LORIS model estimates main and interaction effects in large data frames.
problem Handling large data frames with missing values and explicit modeling of main effects.
method Low-rank interaction and sparse additive effects (LORIS) model with mixed coordinate gradient descent (MCGD).
result LORIS method provides statistical guarantees and converges efficiently for large data sets.
RBMs model binary interactions with hidden node activation effects.
problem Understanding how RBM hidden node activation affects binary variable distributions.
method Investigated RBM marginal distributions with different hidden node activation functions.
result Found exact expressions for RBM marginals as interacting binary variables.
SeqAttnGAN generates interactive images based on multi-turn text descriptions.
problem Interactive image editing with multi-turn textual commands.
method SeqAttnGAN uses a neural state tracker and GAN framework for sequential image generation and refinement.
result SeqAttnGAN outperforms state-of-the-art models on interactive image editing tasks.
Bayesian inference for inverse problems using mean-shift interacting particles
problem Bayesian inference for inverse problems
method Amortized mean-shift interacting particles
result Improves accuracy of Bayesian inference by reducing the number of samples needed
DCN-V2 improves deep & cross network for web-scale learning to rank systems.
problem Efficiently learning feature interactions in large-scale recommender systems.
method Proposes DCN-V2, an improved framework for deep & cross network learning.
result DCN-V2 outperforms state-of-the-art algorithms on benchmark datasets.