A new method for efficient label retrieval in large output spaces.
problem Efficiently retrieving relevant labels for inputs with large output spaces.
method Developed a technique called Stochastic Negative Mining to address the problem of set-valued classifiers in large output spaces.
result Stochastic Negative Mining outperforms existing negative sampling approaches in experiments.
S2M optimizes mining for diverse data subpopulations.
problem Scalability and uniformity in training sets with many labels and diverse data.
method Doubly-stochastic mining (S2M) computes per-example and minibatch losses on hardest labels/examples.
result S2M ensures good performance across all data subpopulations.
We consider the problem of learning a measure of distance among vectors in a feature space and propose a hybrid method that simultaneously learns from similarity ratings assigned to pairs of vectors and class labels assigned to individual vectors. Our method is based on a generative model in which class labels can prov…
Improved financial sentiment analysis using LLMs with retrieval augmentation.
problem Limited performance of traditional NLP models in financial sentiment analysis.
method Retrieval-augmented Large Language Models (LLMs) with instruction tuning.
result Achieved 15% to 48% performance gain in accuracy and F1 score.
Distillation improves simple models by approximating complex labels.
problem Why does distillation improve simple models?
method Statistical perspective on distillation, connecting to extreme multiclass retrieval.
result Distillation helps by approximating underlying class-probabilities, reducing bias and variance.
Proposes Group Loss for deep metric learning to improve clustering and image retrieval.
problem Improving deep metric learning for better clustering and image retrieval.
method Group Loss based on label-propagation method enforcing embedding similarity across all samples of a group.
result Shows state-of-the-art results on clustering and image retrieval on several datasets.
A new hashing method handles complex multi-level labels.
problem Handling complex multi-level labels in cross-modal data retrieval.
method Derives a semantic ranking list from feature and label information, integrates semantic ranking into deep cross-modal hashing.
result RDCMH outperforms other methods in cross-modal retrieval applications.
A new model cleans vocal note event annotations in music.
problem Erroneous labels in music datasets.
method Contrastive learning to automatically create local deformations of likely correct labels.
result Transcription model accuracy improves with the proposed strategy.
Deep neural networks improve music phrase segmentation.
problem Automated melodic phrase detection and segmentation in music.
method Adapted various neural network architectures to symbolic music representation, addressing sparse labeling problem.
result CNN-CRF architecture performs best, offering finer segmentation and faster training.
Prob2Vec embeds problems for adaptive tutoring, achieving high similarity accuracy.
problem Retrieve problems with similar mathematical concepts for adaptive tutoring.
method Hierarchical problem embedding algorithm (Prob2Vec) combining abstraction and embedding steps.
result 96.88% accuracy on problem similarity test, significantly outperforming state-of-the-art sentence embedding methods.
An interactive image retrieval system learns which images in the database belong to a user's query concept, by analyzing the example images and feedback provided by the user. The challenge is to retrieve the relevant images with minimal user interaction. In this work, we propose to solve this problem by posing it as a …
Study compares methods for improving document retrieval accuracy.
problem Improving document retrieval accuracy from large corpora.
method Comparison of query expansion, topic models, and active learning.
result Active learning outperforms keyword lists in most settings.
Recently, digital music libraries have been developed and can be plainly accessed. Latest research showed that current organization and retrieval of music tracks based on album information are inefficient. Moreover, they demonstrated that people use emotion tags for music tracks in order to search and retrieve them. In…
Hashing techniques have been applied broadly in retrieval tasks due to their low storage requirements and high speed of processing. Many hashing methods based on a single view have been extensively studied for information retrieval. However, the representation capacity of a single view is insufficient and some discrimi…
Paper connects sampling and labeling biases in large-output spaces.
problem Efficient training in large-output spaces with label imbalance.
method Unified approach to address sampling and labeling biases.
result Different negative sampling schemes trade-off performance on dominant and rare labels.
Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on "meta-learning…
RDLI integrates domain logic and context grounding to detect crypto anomalies under scarce labels.
problem Extreme label scarcity and evasion strategies in crypto networks.
method Relational Domain Logic Integration (RDLI) with Retrieval Grounded Context (RGC).
result RDLI outperforms GNN baselines by 28.9% in F1 score under 0.01% label scarcity.
DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of labeled data. They ignore the semantically similar and dissimilar constraints bet…
Face recognition system trained with noisy labels.
problem Label noise in training deep learning classifiers.
method Review and apply recent methods to manage noisy annotations.
result Improved performance of face recognition system with noisy labels.
Optimizes tree models for better beam search performance.
problem Beam search causes retrieval performance deterioration in tree models.
method Develops Bayes optimality and calibration under beam search, proposes a novel algorithm for optimal tree model learning.
result Eliminates the training-testing discrepancy in tree models.
New neural network separates singing voices from music using cross entropy loss.
problem Separating singing voices from music accompaniment.
method Deep Convolutional Neural Network (CNN) trained with Ideal Binary Mask (IBM) and cross entropy loss.
result Proposed CNN outperforms existing systems in MIREX evaluations.
We study an extreme scenario in multi-label learning where each training instance is endowed with a single one-bit label out of multiple labels. We formulate this problem as a non-trivial special case of one-bit rank-one matrix sensing and develop an efficient non-convex algorithm based on alternating power iteration. …
Paper explains how early stopping helps distillation in overparameterized neural networks.
problem Understanding how overparameterized neural networks can improve with early stopping.
method Introducing Anisotropic Information Retrieval (AIR) to justify early stopping in distillation.
result Self-distillation algorithm improves over just early stopping, leading to better generalization.
Transformers learn to recall with non-orthogonal embeddings in realistic settings.
problem Understanding how transformers store and retrieve knowledge in practical scenarios.
method Analyzing a single-layer transformer with random embeddings trained on a token-retrieval task.
result Explicit formulas for the model's storage capacity reveal a multiplicative dependence on sample size, embedding dimension, and sequence length.
Generative-discriminative method improves label prediction and instance generation.
problem Difficulty in obtaining high-quality labeled instances.
method Generative-discriminative complementary learning method using CC-GAN.
result Improves accuracy in predicting ordinary labels and generating high-quality instances.
GENRE retrieves entities autoregressively, improving efficiency and accuracy.
problem Retrieving entities from queries efficiently and accurately.
method Autoregressive generation of entity names, reducing memory footprint and improving context encoding.
result Significantly improved performance on entity disambiguation, linking, and retrieval tasks.
Label ranking aims to learn a mapping from instances to rankings over a finite number of predefined labels. Random forest is a powerful and one of the most successful general-purpose machine learning algorithms of modern times. In this paper, we present a powerful random forest label ranking method which uses random de…
We analyze the landscape of empirical risk minimization for high-dimensional models, predicting phase transitions and critical point properties.
problem Understanding the complexity and structure of high-dimensional empirical risk landscapes.
method Using the Kac-Rice formula, we analyze the expected number of critical points and their spectral properties, providing detailed predictions.
result We derive complete topological phase diagrams for the phase retrieval problem, predicting BBP-type transitions and critical point stability.
Semantic labeling for numerical values is a task of assigning semantic labels to unknown numerical attributes. The semantic labels could be numerical properties in ontologies, instances in knowledge bases, or labeled data that are manually annotated by domain experts. In this paper, we refer to semantic labeling as a r…
Graph-RISE learns image embeddings for ultra-fine-grained semantics.
problem Learning image representations for fine-grained semantics.
method Graph-regularized neural graph learning framework.
result Graph-RISE outperforms state-of-the-art on image classification and triplet ranking.
Many radiological studies can reveal the presence of several co-existing abnormalities, each one represented by a distinct visual pattern. In this article we address the problem of learning a distance metric for plain radiographs that captures a notion of "radiological similarity": two chest radiographs are considered …
Over-parameterized models can memorize noisy labels and still generalize well, revealing a hidden structure.
problem Understanding how over-parameterized models can simultaneously memorize noisy labels and generalize well.
method Investigated through modular arithmetic tasks with label noise using two-layer neural networks.
result Over-parameterized models can achieve near-perfect test accuracy with 80% label noise by extracting an internal generalization structure.
The paper proposes a deep learning technique for structured and composable representations.
problem Learning structured and composable representations from input images and discrete labels.
method End-to-end deep learning to learn representations based on distance estimates between class label and contextual information.
result The representations have a clear structure allowing for class and environment decomposition.
Deep neural network predicts semantic labels for source code.
problem Difficulty in labeling and understanding new programming languages and functionalities.
method Language-agnostic deep convolutional neural network trained on Stack Overflow code snippets.
result Mean area under ROC of 0.957 and top-1 accuracy of 86.6% on Github code documents.
This paper introduces PM and PMLP to enhance SSL by considering probability density and cluster assumptions.
problem Insufficient utilization of unlabeled data in SSL.
method Introduces PM to discern similarity and PMLP to consider cluster assumption in label propagation.
result PMLP outperforms other methods in SSL tasks.
Efficient Discrete Supervised Hashing improves cross-modal retrieval by preserving semantic correlations and reducing quantization error.
problem Challenges in preserving semantic correlations and reducing quantization error in cross-modal hashing for large-scale retrieval.
method Collective matrix factorization on heterogenous features and semantic embedding with class labels to learn hash codes efficiently.
result EDSH produces superior performance in both accuracy and scalability over existing methods.
We propose Information-Theoretic Active Learning (ITAL), a novel batch-mode active learning method for binary classification, and apply it for acquiring meaningful user feedback in the context of content-based image retrieval. Instead of combining different heuristics such as uncertainty, diversity, or density, our met…
Systems rank PubMed abstracts and sentences for RDoC criteria, achieving high mAP and MAA.
problem Lack of RDoC labeled datasets and complex labelling process hinder full use of RDoC framework.
method Attention-based neural topic models, supervised and unsupervised sentence ranking models, BM25, BoW, TF-IDF.
result Best systems achieved 1st rank with 0.86 mAP and 0.58 MAA.
Bayesian approach scores influential training examples for model predictions.
problem Enhance interpretability and safety of machine learning models.
method Formulate TDA as a Bayesian information-theoretic problem, scoring subsets by information loss.
result Method aligns with classical influence scores while promoting diversity for subsets.
Active learning selects high-quality examples for text-to-SQL systems.
problem Efficiently annotate large language models for text-to-SQL systems.
method Formalizes example selection as a constrained experimental design problem over semantic query embeddings, proposing a stratified greedy algorithm that maximizes heteroscedastic mutual information.
result Proposed method significantly reduces labeling effort while maintaining high text-to-SQL retrieval accuracy.
LLM forecasting benchmarks suffer from information leakage, which confounds model performance.
problem LLM forecasting benchmarks suffer from information leakage.
method A retrieval-augmented LLM forecaster observes only decision-time information.
result The full pipeline obtains a median monthly Spearman rank IC of +0.154.
The paper tackles fairness in machine learning by modeling latent unbiased labels.
problem Ensuring fairness in machine learning systems that use biased data.
method Explicitly models a latent variable representing a hidden, unbiased label to achieve demographic parity.
result The latent variable approach successfully retrieves fair labels from biased data.
Challenge evaluates semantic code search using annotated corpus.
problem Evaluating relevant code from natural language queries.
method Release of CodeSearchNet Corpus and expert annotations.
result 99 queries with 4k relevance annotations for evaluation.
We consider the problem of personalization of online services from the viewpoint of ad targeting, where we seek to find the best ad categories to be shown to each user, resulting in improved user experience and increased advertisers' revenue. We propose to address this problem as a task of ranking the ad categories dep…
Paper tackles noisy labels for non-decomposable performance measures.
problem Learning from noisy labels for non-decomposable performance measures.
method Designs algorithms for multiclass non-decomposable performance measures using Frank-Wolfe and Bisection methods, corrected for class-conditional noise.
result Noise-corrected algorithms are Bayes consistent, converging to optimal performance.
Extracts main content from web pages using neural sequence labeling.
problem Lack of generalization in existing web page content extraction models.
method Neural sequence labeling model using HTML tags and words as input.
result Model outperforms state-of-the-art and adapts to changes in web page structure.
Adversarial learning improves music transcription accuracy.
problem Conditional independence of labels in deep learning models limits transcription performance.
method Adversarial training scheme operating on time-frequency representations to reduce inter-label dependencies.
result Adversarial learning reduces error rate and increases model confidence.
Improves retrieval accuracy for hierarchical documents, especially for distant matches.
problem Limited expressive power of dual encoder models in hierarchical retrieval.
method Proves feasibility of DEs for HR, introduces pretrain-finetune recipe to improve long-distance retrieval.
result Pretrain-finetune boosts recall on long-distance pairs from 19% to 76%.