Study explores how to explain deep neural networks using interactive naming.
problem Explaining deep neural networks' decisions in human-understandable terms.
method Developed an interactive naming interface for human annotators to cluster activation maps into visual concepts.
result Significant agreement among annotators about visual concepts, many activation maps have recognizable concepts.
We study the collective behavior of interacting agents in a simple model of market economics originally introduced by Nørrelykke and Bak. A general theoretical framework for interacting traders on an arbitrary network is presented, with the interaction consisting of buying (namely, consumption) and selling (namely, pro…
Proposes a new variable grouping approach to improve Bayesian additive regression tree (BART) performance.
problem Improving the predictive performance of BART by reducing nonlinear interactions.
method Variable grouping to identify and separate variables into groups with no nonlinear interactions.
result The proposed GBART method significantly outperforms classical approaches in synthetic and real data experiments.
Loss Data Analytics is an interactive, online, freely available text. The idea behind the name Loss Data Analytics is to integrate classical loss data models from applied probability with modern analytic tools. In particular, we seek to recognize that big data (including social media and usage based insurance) are here…
Proposes a new model for diversified interactive recommendation.
problem Previous methods focus on optimizing recommendation accuracy, ignoring diversity.
method DC2B model using determinantal point process and Thompson sampling-based variational Bayesian inference. result Demonstrates effectiveness of the proposed method through extensive experiments.
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.
Deep models improve GWAS by identifying genetic interactions.
problem Missing non-linear interaction effects in GWAS.
method Gradient-based DeepLIFT technique to interpret deep models.
result Known and novel genetic risk factors identified.
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.
A new method for embedding sparse high-order interactions.
problem Learning embeddings from sparse high-order interaction events.
method Hybridizing sparse hypergraph and matrix Gaussian processes.
result Strong asymptotic bounds on sparsity ratio.
Method detects interactions for better CTR prediction.
problem Predicting click-through rate with high-dimensional categorical features and time-varying interactions.
method Online Random Intersection Chains (ORIC) for detecting informative interactions.
result ORIC detects high-interpretability interactions that improve CTR prediction.
Estimates network structure and interaction rules from multiple agent trajectories.
problem Modeling multi-agent systems on networks from data.
method Jointly infers network topology and interaction kernels using non-convex optimization.
result ORALS estimator is consistent and asymptotically normal under coercivity conditions.
GEM improves recommendation by capturing complex feature interactions.
problem Capturing complex high-order interaction signals in feature-based recommendation models.
method Integrates graph convolution networks to generate high-order embeddings and combines with FM-based models.
result Significant improvement in recommendation performance over baselines.
GSE maps graphs into a space for efficient interaction encoding.
problem Efficiently encoding graph interactions with minimal computations.
method Graph Space Embedding (GSE) maps graphs into a space where interactions are implicitly encoded with minimal computations.
result GSE achieves better performance than traditional algorithms on a real-world clinical dataset.
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.
A new method quickly identifies key variables and interactions.
problem Identifying key variables and interactions in high-dimensional data.
method Kernel trick for sparse orthogonal decomposition in O(# covariates) time.
result Outperforms existing methods for large, high-dimensional data sets.
Methodology for learning sparse models using all multiplicative interactions efficiently.
problem Learning high-order feature interactions with fine control.
method Fine Control Kernel framework, combining Fenchel Duality and Apriori algorithm.
result Efficiently solves large sparse learning problems with sparse feature screening rules.
FGN improves Chinese NER by integrating glyph information and interactive context.
problem Chinese named entity recognition is challenging due to the complexity of characters and their glyphs.
method FGN uses a novel CGS-CNN structure to capture glyph and interactive information, and a sliding window method to fuse BERT and glyph representations.
result FGN achieves state-of-the-art performance on four NER datasets, improving over previous methods.
Two methods improve tensor recovery in Ising models, revealing gene interactions.
problem Improving tensor recovery in Ising models for complex data structures.
method Pseudolikelihood and interaction screening approaches for tensor learning.
result Both methods achieve tensor recovery with sample size logarithmic in nodes, exponential in strength and degree.
BGNN improves GNN by modeling interactions between neighbor nodes.
problem Existing GNN models fail to capture interactions between neighbor nodes, leading to suboptimal performance.
method Proposes a new graph convolution operator that augments the weighted sum with pairwise interactions of neighbor nodes.
result Empirical results show BGNN models outperform traditional GNN models in node classification accuracy.
In many data exploration tasks it is meaningful to identify groups of attribute interactions that are specific to a variable of interest. For instance, in a dataset where the attributes are medical markers and the variable of interest (class variable) is binary indicating presence/absence of disease, we would like to k…
LorentzFM learns feature interactions in a hyperbolic space, reducing parameters and achieving state-of-the-art results.
problem Learning feature interactions for recommendation and CTR predictions using deep learning methods is computationally and memory inefficient.
method Proposes LorentzFM, a model that learns feature interactions in a hyperbolic space, reducing the number of parameters and achieving comparable results.
result LorentzFM achieves comparable and sometimes better results than deep learning methods in recommendation and CTR prediction tasks.
GADGET framework decomposes global feature effects using recursive partitioning.
problem Misleading global feature effects when feature interactions are present.
method Generalized additive decomposition of global effects (GADGET) based on recursive partitioning.
result Minimizes interaction-related heterogeneity of local feature effects.
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.
This paper calculates interaction strength for translation surfaces with multiple singularities.
problem Computing the interaction strength of translation surfaces with multiple singularities is challenging.
method The authors study interaction strength of specific families of translation surfaces, including regular polygons and Bouw-Möller surfaces.
result The paper provides exact computations of KVol on translation surfaces with multiple singularities.
We model a closed economic system with interactions that generates the features of empirical wealth distribution across all wealth brackets, namely a Gibbsian trend in the lower and middle wealth range and a Pareto trend in the higher range, by simply limiting the an agents' interaction to only agents with nearly the s…
Study identifies cancer genes through graph anomaly analysis of protein interactions.
problem Insufficient modeling of biological information in protein interaction networks for cancer gene identification.
method Proposes HIerarchical-Perspective Graph Neural Network (HIPGNN) to detect weight heterogeneity and spectral flattening in cancer gene nodes.
result HIPGNN detects weight heterogeneity and spectral flattening, leading to improved cancer gene identification.
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.
FIVES generates high-order interactive features efficiently and effectively.
problem Automating the generation of high-order interactive features in tabular data.
method Formulates interactive feature generation as edge search on a feature graph, using a GNN and adjacency tensor.
result FIVES outperforms state-of-the-art methods in various datasets and real-world applications.
Predict sepsis early from EHR data with aggregated clinical events.
problem Predict sepsis from clinical data in EHR with temporal interactions.
method Aggregates heterogeneous clinical events, captures temporal interactions with LSTM.
result Achieved high utility score (0.321) in PhysioNet/Computing in Cardiology Challenge 2019.
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.
CatGCN improves GCNs by modeling feature interactions for categorical node features.
problem Suboptimal initial node representations in GCNs due to lack of feature interaction modeling.
method Integrates explicit interaction modeling (local and global) into initial node representation learning for categorical node features.
result CatGCN enhances initial node representations through feature interaction modeling, leading to improved model performance.
New algorithm detects interactions for better individual trait prediction.
problem Tackles the challenge of making accurate individual trait predictions using interactions.
method Extends model-based MDR (MB-MDR) to detect and utilize interactions.
result Outperforms other algorithms in detecting and utilizing interactions for better prediction.
SL2MF predicts synthetic lethality using logistic matrix factorization.
problem Predicting synthetic lethality in human cancers from limited experimental data.
method Logistic matrix factorization incorporating biological knowledge.
result SL2MF effectively predicts known and unknown SL interactions.
VPP learns joint policies for multi-agent RL through interactions.
problem Learning effective joint policies for multi-agent reinforcement learning.
method VPP integrates variational inference into policy layers for efficient sampling and differentiability.
result VPP outperforms previous methods on large-scale multi-agent tasks.
Proposes local coordinate frames for improving model performance in complex dynamical systems.
problem Improving model performance in complex, non-linear, and time-dependent dynamical systems.
method Introduces roto-translation invariant local coordinate frames for geometric graphs.
result The approach outperforms state-of-the-art models in various complex scenarios.
FiBiNET combines feature importance and bilinear interactions for CTR prediction.
problem Improving click-through rate prediction in advertising and feed ranking systems.
method FiBiNET dynamically learns feature importance via SENET and bilinear feature interactions.
result FiBiNET outperforms shallow and deep models on real-world datasets.
ONN learns different representations for different operations to improve user response prediction.
problem Improving user response prediction in online advertising and recommendation systems.
method Proposes Operation-aware Neural Networks (ONN) to learn different representations for different operations.
result ONN consistently outperforms state-of-the-art models in both offline and online environments.
Integrates CF and RL for collaborative recommendation.
problem Interactive recommendation problem where current recommendations affect future quality.
method Develops CFRL, a novel approach that models as an RL task and learns optimal policy.
result Demonstrates superior performance compared to existing methods on real-world datasets.
Using holographic renormalization coupled with the Caffarelli/Silvestre\cite{caffarelli} extension theorem, we calculate the precise form of the boundary operator dual to a bulk scalar field rather than just its average value. We show that even in the presence of interactions in the bulk, the boundary operator dual to …
GTI network learns linguistic features for multi-task sequence tagging.
problem Improving neural model performance on multi-task sequence tagging without explicit features.
method GTI network with neural gate modules to learn relations between tasks.
result GTI network outperforms baselines on chunking and NER tasks.
We observe standard transfer learning can improve prediction accuracies of target tasks at the cost of lowering their prediction fairness -- a phenomenon we named discriminatory transfer. We examine prediction fairness of a standard hypothesis transfer algorithm and a standard multi-task learning algorithm, and show th…
We translate into the double forms formalism the basic identities of Greub and Greub-Vanstone that were obtained in the mixed exterior algebra. In particular, we introduce a second product in the space of double forms, namely the composition product, which provides this space with a second associative algebra structure…
Quadratic discriminant analysis (QDA) is a standard tool for classification due to its simplicity and flexibility. Because the number of its parameters scales quadratically with the number of the variables, QDA is not practical, however, when the dimensionality is relatively large. To address this, we propose a novel p…
We present a neural model for representing snippets of code as continuous distributed vectors ("code embeddings"). The main idea is to represent a code snippet as a single fixed-length code vector, which can be used to predict semantic properties of the snippet. This is performed by decomposing code to a col…
Discussing issues in robust clustering, especially with Gaussian models.
problem Handling outliers and ambiguity in clustering groups.
method Focus on Gaussian mixture model, examining formal definitions, interactions, and tuning decisions.
result Outliers can confuse clustering groups and existing stability measures fail with them.
Systemic risk in banking systems remains a crucial issue that it has not been completely understood. In our toy model, banks are exposed to two sources of risks, namely, market risk from their investments in assets external to the banking system and credit risk from their lending in the interbank market. By and large, …
Framework enables robots to learn tasks from unlabeled human instructions.
problem Robotic task learning with unlabeled human instructions.
method TICS architecture combining reward function, human feedback, and unlabeled instructions.
result Framework accelerates task-learning and reduces teaching signals.
SeqFM models dynamic and sequential features for better predictive analytics.
problem Inadequate handling of sequential dependencies in existing FM-based models.
method Introduces SeqFM, a novel model that incorporates multi-view self-attention to model static, dynamic, and their interactions.
result SeqFM outperforms existing models in ranking, classification, and regression tasks on six large-scale datasets.