User-specific KWS system learns new keywords on-device.
problem Out-of-vocabulary problem in traditional KWS systems.
method Query-by-example enrollment and testing, using phonetic posteriors and FST.
result Promising performance on two keywords, preserving simplicity.
Transfer learning improves activity recognition accuracy on smartwatches.
problem Inconsistent activity recognition accuracy across different users.
method On-device calibration of GBM by tuning parameters without retraining.
result Significant improvement in user-based accuracy for activity recognition.
A graph traversal algorithm for cold-start news recommendation using named entities.
problem Cold-start news recommendation for articles without user-specific information.
method Graph traversal algorithm and novel weighting scheme for named entities over a knowledge graph.
result Our method produces stronger Pearson correlation to human similarity scores than other cold-start methods.
Model learns individual preferences for photo aesthetics.
problem Lack of personalized aesthetics models in photography.
method Residual learning approach to adapt to individual preferences.
result Surpasses state-of-the-art methods in predicting aesthetic value.
Formulates approach for guiding explanation types based on user specifications.
problem Creating explainable AI components from user-defined specifications.
method Develops a method for generating explanations based on user-defined specifications.
result Demonstrates feasibility of user-defined explanations for complex models like Bayesian networks and graph neural networks.
Develops a two-level monotonic multistage recommender system for better user-specific prediction.
problem Leveraging user-item-stage dependencies in a monotonic chain of events for enhanced prediction accuracy.
method A multistage recommender system with a two-level monotonic property, using a large-margin classifier based on a nonnegative additive latent factor model.
result The proposed method outperforms existing methods in simulations and an article sharing dataset.
Real-time personalization for HAR models learns from new users without prior data.
problem Poor performance of HAR models on new users without labeled data.
method Incremental online domain adaptation using batch normalization.
result Personalized HAR models adapt to new users in real-time.
Decouples data privatization from user preferences for privacy-preserving data.
problem Privacy-preserving data with user-specific private information.
method Decouples data privatization from user preferences using a Variational Autoencoder (VAE) and a generative filter trained by a GAN-type robust optimization.
result Effective privatization of data with minimal disturbance to utility, as shown by experiments on MNIST, UCI-Adult, and CelebA.
A new method models user-specific parameters as a low-rank plus sparse component for efficient personalization.
problem Efficient personalization of machine learning models for individual users.
method Meta-learning approach that models network weights as a sum of low-rank and sparse components.
result The proposed method, AMHT-LRS, achieves nearly optimal sample complexity for estimating the low-rank and sparse components.
KGNN-LS improves recommender systems using knowledge graphs and label smoothness.
problem Improving recommender systems through better user-item embeddings.
method KGNN-LS combines knowledge graphs, user-specific embeddings, and label smoothness regularization.
result KGNN-LS outperforms state-of-the-art baselines and handles cold-start scenarios.
We study the problem of collaborative filtering where ranking information is available. Focusing on the core of the collaborative ranking process, the user and their community, we propose new models for representation of the underlying permutations and prediction of ranks. The first approach is based on the assumption …
New bounds for LDP with heterogeneous privacy levels guaranteeing high probability of accuracy.
problem Statistical estimation under LDP with users having varying privacy levels.
method Developed finite sample upper bounds in ℓ_2-norm with high probability, complemented by lower bounds.
result Optimal guarantees for heterogeneous LDP in terms of probability and constants.
Item-item collaborative filtering (CF) models are a well known and studied family of recommender systems, however current literature does not provide any theoretical explanation of the conditions under which item-based recommendations will succeed or fail. We investigate the existence of an ideal item-based CF method a…
Summarizes financial news for better investment decisions.
problem Information overload from financial news hinders timely investment decisions.
method Personalized Chain-of-Thought summarization framework integrating user-specified keywords.
result Personalized summaries highlight relevant market signals, improving investment narratives.
A GPU framework speeds up BnB for discrete optimization problems.
problem Optimizing large-scale discrete problems with GPU limitations.
method Parallel BnB nodes in GPU batches, using padding and custom kernels.
result One to two orders of magnitude speedup and zero optimality gap.
Visualizes futures markets using particle physics tools.
problem Understanding high-velocity data in futures markets.
method Uses ROOT, an open-source data-analysis tool, to reconstruct and visualize message-based data.
result Allows stakeholders to gain a better understanding of markets and monitor effectively.
Silas provides transparent, verifiable machine learning models.
problem Creating reliable and explainable machine learning models.
method Formal verification, correct training, and transparent reasoning modules.
result Silas models are formally verified and correct.
FedMAX tackles activation divergence in FL, improving accuracy and efficiency.
problem Activation divergence in Federated Learning due to non-IID data.
method Introduced a prior based on maximum entropy to minimize information about per-device activation vectors and make similar classes more alike.
result Significantly more similar activation vectors across multiple devices, leading to better accuracy and efficiency.
Federated Learning (FL) systems are gaining popularity as a solution to training Machine Learning (ML) models from large-scale user data collected on personal devices (e.g., smartphones) without their raw data leaving the device. At the core of FL is a network of anonymous user devices sharing training information (mod…
In the field of exploratory data mining, local structure in data can be described by patterns and discovered by mining algorithms. Although many solutions have been proposed to address the redundancy problems in pattern mining, most of them either provide succinct pattern sets or take the interests of the user into acc…
This work frames reward modelling from preferences as a causal problem.
problem Reward modelling from preference data for AI alignment.
method Causal inference approach to identify challenges and assumptions.
result Causally-inspired approaches improve model robustness.
The paper uses model-based trees to create interpretable surrogate models for complex machine learning models.
problem Interpreting complex machine learning models.
method Using model-based trees to partition feature space and create interpretable models.
result Model-based trees generate optimal surrogate models that balance interpretability and performance.
Study evaluates relevance metrics for similarity-based model explanations.
problem Providing understandable explanations for complex model predictions.
method Evaluated three relevance metrics using three tests.
result Cosine similarity of gradients performs best for explanations.
New method compresses random forest models for efficient storage.
problem Large storage requirements for ensemble models like random forests.
method Probabilistic modeling of trees followed by model clustering.
result High compression rates and perfect reconstruction of original ensembles.
Study on hyperparameter optimization for smartphone-based HAR.
problem Maintaining stable classification accuracy in HAR systems with mobile devices.
method Semi-supervised classifier and study on hyperparameter configuration.
result Adjusting hyperparameters can maintain classification accuracy.
We propose a novel parameterized family of Mixed Membership Mallows Models (M4) to account for variability in pairwise comparisons generated by a heterogeneous population of noisy and inconsistent users. M4 models individual preferences as a user-specific probabilistic mixture of shared latent Mallows components. Our k…
MetaSelector learns to choose the best model for each user.
problem Heterogeneous datasets and user-specific historical data make it hard to find the best model for each user.
method Meta-learning framework to train a model selector that chooses the best model for each user based on their historical data.
result MetaSelector outperforms single model and sample-level model selector in AUC and LogLoss.
In this paper, we propose a listwise approach for constructing user-specific rankings in recommendation systems in a collaborative fashion. We contrast the listwise approach to previous pointwise and pairwise approaches, which are based on treating either each rating or each pairwise comparison as an independent instan…
XploVAE improves recommendation by balancing known and novel items.
problem Balancing known and novel items for better recommendations.
method Constructs user-specific subgraphs for exploitation and exploration, learns personalized item embeddings.
result Demonstrates effectiveness on various real-world datasets.
CoLoRA leverages task similarity to boost fine-tuning efficiency.
problem Efficiently fine-tuning large foundation models with scarce labeled data.
method CoLoRA trains a shared adapter for task similarity and personalized adapters for user-specific tasks.
result CoLoRA significantly boosts fine-tuning performance when tasks are similar.
Automates feature extraction for IMU-based activity recognition.
problem Manual feature engineering is time-consuming and limits IMU-based applications.
method FRESH algorithm for automated feature extraction.
result Workflow automates feature extraction from synchronized IMU sensors.
Proposes efficient user cold start recommendation via meta parameter partition.
problem User cold start in recommendation systems.
method Divides model parameters into fixed and adaptive parts, learning them separately offline and online.
result Significant improvement in AUC (2.48% absolute improvement).
When tracking user-specific online activities, each user's preference is revealed in the form of choices and comparisons. For example, a user's purchase history is a record of her choices, i.e. which item was chosen among a subset of offerings. A user's preferences can be observed either explicitly as in movie ratings …
Study uses attention-based method to detect different types of online harassment.
problem Detecting different types of online harassment in social media content.
method Multi-attention based approach using Recurrent Neural Networks to address imbalanced data.
result Demonstrates effectiveness of attention-based mechanism for detecting various types of online harassment.
An important metric of users' satisfaction and engagement within on-line streaming services is the user session length, i.e. the amount of time they spend on a service continuously without interruption. Being able to predict this value directly benefits the recommendation and ad pacing contexts in music and video strea…
Proposes TEMN for better POI recommendations.
problem Challenges in capturing user preferences and spatio-temporal POI relationships.
method Integrates topic model and memory network, incorporating geographical module.
result Improves POI recommendation effectiveness by 3.25% and 29.95%.
Bayesian Robust Optimization for Imitation Learning (BROIL) balances risk and reward.
problem Learning robust policies for new states in imitation learning.
method Bayesian reward function inference and user-specific risk tolerance.
result BROIL outperforms risk-sensitive and risk-neutral algorithms.
New testing method for robust actor-critic bandit algorithms.
problem Balancing data collection for app performance and user adherence.
method Modified actor-critic algorithm and novel testing procedure.
result Testing procedure is robust to critic misspecification.
Recommendation is the task of improving customer experience through personalized recommendation based on users' past feedback. In this paper, we investigate the most common scenario: the user-item (U-I) matrix of implicit feedback. Even though many recommendation approaches are designed based on implicit feedback, they…
MDLdroid improves mobile deep learning for personal sensing with faster training.
problem Continuous local changes and resource constraints in personal mobile sensing affect global model performance.
method ChainSGD-reduce approach to reduce overhead and balance resources.
result 2x to 3.5x faster training on off-the-shelf mobile devices compared to single-device training.
RNE tackles scalable recommendation for billion-scale scenarios.
problem Designing a scalable recommendation system for diverse and dynamic user interests.
method RNE uses a diversity- and dynamics-aware neighbor sampling method for scalable network embedding.
result RNE achieves high-quality and diverse results on a billion-scale user-item graph.
We establish the first benchmark for federated learning with differential privacy in ASR, achieving competitive performance.
problem Challenges in training large transformer models for ASR in federated learning with differential privacy.
method Per-layer clipping and layer-wise gradient normalization to mitigate gradient heterogeneity.
result FL with DP is viable in ASR with strong privacy guarantees, achieving competitive performance.
Study shows Julia sets and gasket limit sets are quasiconformally different.
problem Quasiconformal non-equivalence of Julia sets and gasket limit sets.
method Proved quasiconformal non-equivalence of Julia sets and gasket limit sets.
result Julia sets and gasket limit sets are quasiconformally different.
New deep learning model for matching sets of items, preserving exchangeability.
problem Matching two different sets of items while preserving exchangeability.
method Exchangeable deep neural networks architecture and efficient training framework.
result Significant improvements in fashion set recommendation and group re-identification.
Study shows non-symmetric convex sets have full boundary limits.
problem Understanding boundaries of non-symmetric convex sets.
method Proved using proximal limit set analysis.
result Proximal limit set equals full projective boundary for non-symmetric irreducible divisible convex sets.
The paper analyzes set-to-set matching with neural networks, focusing on theoretical generalization.
problem Theoretical analysis of set-to-set matching with neural networks.
method Generalization error analysis of set-to-set matching with neural networks.
result Theoretical insights into the behavior of set-to-set matching models.
Generative model learns to autoencode and generate sets of images.
problem Learning to represent and generate sets of images with unknown number of sets.
method Set Distribution Networks (SDNs) learn set encoder, discriminator, generator, and prior.
result SDNs can reconstruct and generate sets of images with preserved attributes.
Study on cold and freezing sets in digital images.
problem Properties of cold sets in digital images.
method Analysis of properties and relationships between cold and freezing sets.
result Examined relationships between cold and freezing sets.