Modeling user check-ins in social networks to predict future behavior.
problem Predicting future user movements and influence in location-based social networks.
method Probabilistic model based on doubly stochastic point process with periodic decaying kernel for time and time-varying multinomial distribution for location.
result The proposed model outperforms other alternatives in predicting user check-ins.
SANST uses self-attentive networks with spatial and temporal embeddings for better POI recommendations.
problem Next point-of-interest (POI) recommendation for users based on their history.
method SANST incorporates spatio-temporal patterns into self-attentive networks.
result SANST outperforms state-of-the-art models by up to 13.65% in nDCG@10.
Study analyzes WiFi check-ins to predict student activities.
problem Limited understanding of daily routines in POI prediction.
method Heterogeneous graph-based method to encode correlations.
result Improved POI prediction on education check-in data.
The paper uses WeChat data to map urban cultural resource needs.
problem Optimizing cultural resource allocation in cities.
method Data-driven framework using WeChat user check-ins and temporal LDA model.
result Identifies urban regions lacking cultural resources.
New method amplifies privacy in decentralized learning without centralized communication.
problem Privacy amplification in decentralized federated learning.
method Random check-in protocol for DP-SGD in FL.
result Privacy/accuracy trade-offs similar to subsampling/shuffling, but without server-initiated communication.
Task focuses on fact checking in Q&A forums, improving over baseline systems.
problem Fact checking in community Q&A forums to distinguish factual from opinion.
method Two subtasks: distinguishing factual vs. opinion/advice/socializing, predicting answer truthfulness.
result Improved over baseline systems for both subtasks, but not for Subtask B.
GCNs model complex spatial patterns of POI check-ins.
problem Capturing complex spatial patterns in irregular data.
method Graph Convolutional Neural Networks (GCNs) for semi-supervised prediction.
result Demonstrates feasibility of GCNs for complex geographic data.
Ranked second in fact-checking task, using DRR NN with embeddings.
problem Fact-checking questions in community forums.
method Deeply Regularized Residual Neural Network (DRR NN) with Universal Sentence Encoder embeddings, ensemble methods.
result Ranked second in fact-checking task.
The paper models crime risk using Foursquare check-ins and mobility data.
problem Understanding and predicting crime risk in urban areas.
method Directed graph of aggregated movement data, region risk factor derivation, DIFFER features.
result Reliable correlations between DIFFER features and crime count observed.
Paper checks SSC for matrix factorizations using Gurobi.
problem Checking the SSC for various matrix factorizations.
method Formulated as a non-convex quadratic optimization problem over a bounded set, solved with Gurobi.
result SSC can be checked in reasonable time for realistic scenarios.
A new Gaussian mechanism for differential privacy in the shuffle model is introduced.
problem Improving differential privacy in distributed learning environments.
method Characterization and upper-bounding of Rényi differential privacy (RDP) for the shuffle Gaussian mechanism.
result The shuffle Gaussian mechanism provides improved privacy guarantees compared to existing methods.
The paper models SaaS products as insurance, offering new pricing tools.
problem Modeling capped-usage SaaS products with insurance principles.
method Frequency-severity decomposition, premium calculation, Monte Carlo simulations.
result SaaS pricing can be analyzed using insurance actuarial methods.
For each k > 0 we find an explicit function f_k such that the topology of S inside the ball B(p,r) is `bounded' by f_k(r) for every complete Riemannian surface (compact or noncompact) with K\geq -k^2, every point p on the surface, and every r. Using this result, we obtain a characterization (simple to check in practica…
In this note we prove that the volume of a causal diamond associated with an inertial observer in asymptotically de Sitter 4-dimensional space-time is monotonically increasing function of cosmological time. The asymptotic value of the volume is that of in maximally symmetric de Sitter space-time. The monotonic property…
Paper proposes a new model for multivariate risk measures using Wasserstein barycenters.
problem Estimating robust multivariate risk measures in financial markets.
method Wasserstein barycenters of probability measures, copulas, Value at Risk models.
result The new model provides realistic VaR forecasts in both common and volatile periods.
Constructs Lagrangians in Calabi-Yau threefolds using tropical curves.
problem Constructing Lagrangian structures in Calabi-Yau threefolds.
method Tropical curves and toric degeneration techniques.
result Constructs multiple Lagrangian rational homology spheres with specific weights.
Many normal subgroups of mapping class groups are geometric.
problem Characterizing normal subgroups of mapping class groups of surfaces with punctures.
method Proving automorphism and commensurator groups of certain subgroups are isomorphic to the mapping class group, using simplicial complexes.
result Many normal subgroups of mapping class groups are geometric.
We introduce trading fees into AMM models and analyze their impact on swap rates and profits.
problem The impact of trading fees on AMM models and users' trading strategies.
method We extend a foundational AMM model by introducing a trading fee parameter and analyze the model using economic and mathematical rigor.
result Trading fees affect the additivity of swap rates and can lead to greater profits from larger trades.
Optical (or Robinson) structures are one generalisation of four-dimensional shearfree congruences of null geodesics to higher dimensions. They are Lorentzian analogues of complex and CR structures. In this context, we extend the Goldberg-Sachs theorem to five dimensions. To be precise, we find a new algebraic condition…
hood2vec identifies urban area similarity via mobility networks.
problem Identifying similar urban areas using mobility networks.
method Learning node embeddings of the mobility network from Foursquare check-ins.
result Mobility dynamics capture different aspects of urban area similarity than venue types.
Refined 3D index uses surgery and gradings to distinguish 3-manifolds.
problem Distinguishing 3-manifolds and gauge theories phases.
method Dehn surgery presentation, ideal triangulation, and enhanced flavor symmetries.
result Invariance of refined index under various transformations.
Study tests adequacy of FARIMA models with uncorrelated but non-independent errors.
problem Testing adequacy of FARIMA models with specific error characteristics.
method Derive asymptotic distributions of residual autocovariances and autocorrelations, propose self-normalization approach.
result Asymptotic distributions of modified portmanteau statistics for weak FARIMA models.
Derives equations for non-abelian self-dual strings and finds a categorified monopole solution.
problem Derives equations for non-abelian self-dual strings.
method Derives equations of motion for non-abelian self-dual strings using string 2-group and categorified principal bundle.
result Derives equations of motion and finds a categorified monopole solution.
GUIDE-VAE generates user-guided data with improved realism and performance.
problem Generating data points for multi-user datasets while considering user information.
method Conditional generative model that integrates user embeddings and a pattern dictionary-based covariance composition.
result GUIDE-VAE outperforms conventional VAEs in multi-user settings, especially under data imbalance.
The paper analyzes and optimizes recommendation systems using user-user and item-item collaborative filtering.
problem Optimizing recommendation systems to minimize disliked recommendations.
method Proposes algorithms inspired by user-user and item-item collaborative filtering, proving performance guarantees in terms of expected regret.
result Information-theoretic lower bounds on regret match upper bounds up to logarithmic factors in two model parameter regimes.
Hybrid approach combines user feedback and machine learning for predicting user satisfaction.
problem Measuring user satisfaction in large-scale conversational agent systems.
method Fusion of explicit user feedback and predictions from two machine-learned models trained on different data types.
result Hybrid approach significantly improves user satisfaction predictions.
Author2Vec generates user embeddings from social media data.
problem Generating useful user embeddings from noisy social media data.
method End-to-end neural network with BERT sentence representations and unsupervised pre-training.
result Author2Vec outperforms traditional methods in user classification tasks.
Optimal recommendation system using user and item clustering.
problem Maximizing recommendation accuracy with limited feedback.
method Latent variable model with user and item clustering, exploiting i.i.d. structure.
result Near-optimal algorithm that combines item and user structures.
CnGAN generates synthetic user preferences for non-overlapped users in cross-network recommender systems.
problem Cross-network recommender solutions ignore non-overlapped users, limiting their applicability.
method Multi-task learning, encoder-GAN architecture, user-based pairwise loss function.
result Generated user preferences improve recommendations for non-overlapped users, achieving superior performance.
FAIRY explains user actions and social media feeds.
problem Users struggle to understand why certain items appear in their social feeds.
method FAIRY uses an interaction graph to model user behavior and ranks feed items, scoring paths connecting user actions and feed items.
result FAIRY provides clear explanations for user actions and feed items, enhancing transparency and user understanding.
The paper proposes a method to learn user representations invariant to social media behavior changes.
problem Difficulty in comparing users over time due to evolving behavior.
method Learning a mapping from user activity to a vector space capturing invariant features.
result The learned mapping enables efficient comparisons of users not seen at training time.
New algorithms for uncoordinated spectrum access with multi-user multi-armed bandits.
problem Uncoordinated spectrum access with unknown number of users and channels.
method Developed algorithms for stochastic and adversarial settings, combining Exp3.P for dynamic scenarios.
result Sub-linear regret guarantees for both stochastic and adversarial cases, even when users outnumber channels.
Paper proposes a combined model for better recommendation by integrating explicit and implicit feedbacks.
problem Improve recommendation accuracy by considering both explicit and implicit feedbacks.
method Developed three models (RHC-PMF, RV-PMF, RHCV-PMF) that incorporate users' explicit and implicit feedbacks for better rating prediction.
result RHCV-PMF model outperforms other models in cold start scenarios for both users and items.
New method detects and measures malicious users in recommendation algorithms.
problem Identifying and quantifying malicious user activity in recommendation systems.
method Probabilistic programming for a disentangled model of malicious and regular user behavior.
result Simulation-based measure for quantifying malicious user effects.
Proposes CF-SFL to improve sparse data recommendation.
problem Poor performance of CF in sparse data.
method Generative user feedback loop to simulate user feedback.
result Improves recommendation results on multiple datasets.
A method to prevent overfitting by modeling user knowledge in interactive machine learning.
problem Overfitting due to user reinforcement of noisy patterns in training data.
method User modelling based on rational behavior to correct overfitting.
result Improves predictive performance in sentiment analysis tasks.
New policy reduces spectrum access regret in uncoordinated systems.
problem Uncoordinated spectrum access with user-dependent rewards.
method Multi-user multi-armed bandit (MAB) model with user-specific rewards.
result Achieves O(logT) regret for spectrum access. FairJudge identifies fraudulent users in rating platforms.
problem Untrustworthy users giving fraudulent ratings.
method Three metrics: fairness, reliability, and goodness; iterative algorithm to predict these metrics.
result Significantly outperforms existing algorithms in predicting fair and unfair users.
Optimal method identifies users from anonymized behavioral data histograms.
problem Identifying users from anonymized behavioral data histograms.
method Matching histograms from two datasets, one anonymized, one known.
result A large fraction of users can be identified using histograms, acting as fingerprints.
Paper uses RNN to predict SaaS user lifetime value.
problem Predicting user lifetime value in SaaS applications.
method Recurrent Neural Network with multi-cell architecture, accounting for cohort, age-in-system, and contemporaneous information.
result Significantly improved prediction accuracy compared to existing models.
The paper tackles robust policy learning in multitask contextual bandits with adversarial users.
problem Learning optimal policies in multitask contextual bandits with a small fraction of adversarial users.
method Developed efficient robust mean estimators for both uni-variate and high-dimensional random variables.
result Lower bound of ildeΩ(min(S,A)⋅α2/ε2) per-user interactions to learn an ε-optimal policy for good users. Improved neural model for social recommendation by integrating social and interest networks.
problem Data sparsity and lack of higher-order relationships in social recommendation.
method DiffNet++ models neural influence diffusion and interest diffusion in a unified framework using a multi-level attention network.
result Extensive experiments on real-world datasets show the effectiveness of DiffNet++.
Decomposes flat nonlinear discrete-time systems into simpler components.
problem Flatness of nonlinear discrete-time systems.
method Coordinate transformations and feedback, using flow-box and Frobenius theorems.
result Flatness of a discrete-time system can be checked algorithmically.
DBRec discovers latent groups to improve recommendation.
problem Sparse user-item interaction data in recommender systems.
method Simultaneously discovers latent user/item groups and interacts them with users/items for bridging preferences.
result DBRec outperforms state-of-the-art models on real datasets.
The paper develops models to influence user interests in recommendation systems.
problem Recommendation systems assume rigid user interests, ignoring the effect of learning strategies.
method Develops influence models for a learning algorithm that optimally recommends websites.
result The models show how learning strategies can influence steady user interests and optimal strategies.
Study personalizes user experience to maximize rewards with patience budget.
problem Maximizing rewards for a platform while respecting user patience.
method Proposes bandit algorithms for sequential choice with feedback models.
result Upper and lower bounds on regret of order O(N2/3) and Ω(N2/3). Estimates population mean from user-level data with privacy, accounting for heterogeneity.
problem Heterogeneous user data with varying numbers of data points and distributions.
method Simple model of heterogeneous user data, differential privacy mechanism for estimation.
result Asymptotic optimality of the proposed estimator and general lower bounds on error.
Intelligent recommender system tracks user activity and intent for better recommendations.
problem Recommender systems often lack user intent awareness, leading to suboptimal recommendations.
method Encoded user activity, reduced to lower dimensions using tensor factorization, and scored for intent. Combined with contextual information for ranking recommendations.
result Better recommendations compared to baselines, with intent-aware scoring.