Proposes a graph-based text representation for improved sentiment analysis.
problem Lack of effective methods to encode semantic relations in textual data for sentiment analysis.
method Sentence-level graph-based text representation with deep neural network.
result Significantly outperforms existing sentiment analysis approaches on benchmark datasets.
Proposes a hybrid model for stock market report classification using graph neural networks.
problem Lack of unified node embeddings for heterogeneous graphs in text datasets.
method Transductive hybrid approach combining unsupervised node representation learning and supervised node classification/edge prediction.
result Demonstrates the model's ability to classify stock market technical analysis reports.
GEAR uses graphs to integrate and reason over multiple evidence for fact verification.
problem Fact verification requires integrating and reasoning over multiple pieces of evidence.
method GEAR employs a graph-based framework to transfer information among evidence and uses BERT for improved performance.
result GEAR achieves a promising test FEVER score of 67.10% on a large-scale benchmark dataset.
AUC-spec optimizes graph-based SSL for complex label distributions.
problem Training accurate models with scarce labeled data and abundant unlabeled data.
method Computes a low-dimensional representation that maximizes class separation via AUC optimization.
result AUC-spec achieves competitive results on synthetic and real-world datasets.
Graph-based state representation improves deep RL performance.
problem High sample-complexity and starting with a good input representation in deep RL.
method Exploiting the graph structure of MDPs for effective state representation learning.
result Graph-based node representation methods outperform matrix-based methods in grid-world navigation tasks.
An unsupervised method clusters patient incident reports for content analysis.
problem Lack of methods to extract interpretable content from electronic healthcare records.
method Combines text-embedding with paragraph vectors and graph-theoretical multiscale community detection.
result Extracts high-intrinsic-consistency groups of patient incident reports.
SMILES Transformer learns molecular fingerprints for drug discovery.
problem Poor performance of rule-based molecular fingerprints in shallow prediction models or small datasets.
method Unsupervised pre-training of a sequence-to-sequence language model on a corpus of SMILES.
result SMILES Transformer outperformed existing methods in small-data settings.
RPS uses graph-based representation learning for better portfolio optimization.
problem Improving portfolio optimization with better returns and lower risks.
method RPS redefines the distance matrix of financial assets using Representation Learning and Clustering algorithms.
result RPS proposes a heuristic to select closer to the optimal subset of assets.
Novel graph-based framework for hyperspectral image classification using superpixels.
problem High classification accuracy with limited labelled data in hyperspectral images.
method Superpixel method for defining local regions, spectral and spatial features extraction, contracted graph representation, semi-supervised classifier.
result Our approach produces accurate classifications with minimal labelled data, outperforming state-of-the-art techniques.
ProGraML uses graph-based machine learning to improve program optimization and analysis.
problem Improving program optimization and analysis with machine learning.
method Low-level, language agnostic graph representation and message passing neural networks.
result ProGraML achieves an average 94.0 F1 score on a benchmark dataset, significantly outperforming state-of-the-art approaches.
Proposes learning a hierarchical prior in VAEs to avoid over-regularization.
problem Over-regularization in VAEs with standard normal priors.
method Formulates as a constrained optimisation problem, introduces graph-based interpolation.
result Learned latent representation reflects data manifold topology and properties.
In this paper, we present a graph-based semi-supervised framework for hyperspectral image classification. We first introduce a novel superpixel algorithm based on the spectral covariance matrix representation of pixels to provide a better representation of our data. We then construct a superpixel graph, based on carefu…
Graph-based Bayesian SSL uses graph theory to propagate labels from a few to many unlabeled features.
problem Efficiently propagating labels from a small set of labeled data to a large set of unlabeled data.
method Probabilistic framework using graph theory and Bayesian statistics.
result Mathematical foundations for improving the accuracy and efficiency of label propagation.
A new text representation model combines CNN and VAE for better semantic extraction.
problem Difficult to effectively extract semantic features and distinguish polysemy in text data.
method Integrates CNN for feature extraction and VAE for consistent Gaussian distribution.
result The model outperforms traditional classification algorithms in text classification tasks.
Paper proposes a novel GCN-based SSL algorithm to enhance node representations using contrastive and generative losses.
problem Shortage of supervision in graph-based semi-supervised learning.
method Combines contrastive and generative graph convolutional networks to enrich supervision signals.
result Improves node representations and classification results on various real-world datasets.
Automates text mining by learning effective representations from raw text.
problem Limited automation in text mining for non-experts.
method Meta-learning approach to automatically obtain text representations.
result Proposed methodology yields highly effective text classification pipelines.
TextNAS finds optimal text representation networks using neural architecture search.
problem Finding the optimal text representation networks is challenging.
method Proposes a novel search space for text representation and uses automatic neural architecture search.
result Automatic search discovers network architectures that outperform state-of-the-art models on text classification and natural language inference tasks.
All SMILES VAE learns molecule latent representations from SMILES strings.
problem Non-unique SMILES strings and high computational cost of graph convolutions hinder VAEs for molecular property optimization.
method Stacked recurrent neural networks encode multiple SMILES strings, pooling hidden representations, and attentional pooling builds a final latent representation.
result All SMILES VAE significantly surpasses state-of-the-art in molecular property optimization tasks.
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most existing approaches require that all nodes in the graph are present during training of the embeddings; these previous approaches …
New method removes lexical treatment signals to avoid overlap violations in causal inference from text.
problem Overlap violations in estimating causal effects from text due to treatment encoding.
method Masking-based adjustment representations to remove lexical treatment signals.
result Masking improves overlap diagnostics and reduces bias in treatment effect estimates.
W-RNN improves text classification by extracting serialized text semantics.
problem Semantic constraint in sparse representation classification methods.
method Weighted RNN using word vectors and recurrent neural networks.
result W-RNN outperforms other methods in precision, recall, F1, and loss values.
A method for disentangling text representations without supervision.
problem Challenges in learning disentangled representations of natural language.
method Information-theoretic guidance to induce independent style and content embeddings.
result High quality disentangled representations in terms of content and style preservation.
GraphCNNpred predicts stock market indices using deep learning.
problem Predicting stock market trends with diverse datasets.
method Graph-based CNN model for feature extraction.
result Improves prediction performance by 4% to 15% in F-measure.
Novel graph-based approach segments financial integration eras.
problem Assessing worldwide financial integration using data patterns.
method 3-step approach combining graph-based representations and optimization.
result Endogenous stable eras of world-wide financial integration found.
Proposes a method to learn a low-rank kernel matrix for graph-based clustering.
problem Challenges in learning an optimal kernel matrix for graph-based clustering.
method Unified framework for graph construction and kernel learning, focusing on a low-rank kernel matrix.
result Efficacy of the proposed method validated through extensive experiments.
Paper introduces graph-based transforms for video compression.
problem Efficiently represent video signals for compression.
method Develops two techniques for designing graph-based transforms (GL-GBTs and EA-GBTs).
result Graph-based transforms outperform traditional KLT in video compression.
Improved autoencoders guide latent sentence representations for better text generation and manipulation.
problem Current autoencoders struggle to maintain coherent latent spaces for meaningful text manipulations.
method Adversarial autoencoders with a denoising objective (DAAE) to guide latent space geometry.
result DAAE provides the best trade-off between generation quality and reconstruction capacity.
New text-to-image diffusion models improve scene understanding for AI agents.
problem Fine-grained scene understanding for AI agents from text and images.
method Pre-trained text-to-image diffusion models optimized for generating images from text prompts.
result Policies learned with Stable Control Representations outperform state-of-the-art approaches on various control tasks.
We review the current state of automatic differentiation (AD) for array programming in machine learning (ML), including the different approaches such as operator overloading (OO) and source transformation (ST) used for AD, graph-based intermediate representations for programs, and source languages. Based on these insig…
Let Mφ be a surface bundle over a circle with monodromy φ:S→S. We study deformations of certain reducible representations of π1(Mφ) into SL(n,C), obtained by composing a reducible representation into SL(2,C) with the irreducible representation $\text{SL}(2,\mathb…
We establish a gluing construction for Higgs bundles over a connected sum of Riemann surfaces in terms of solutions to the Sp(4,R)-Hitchin equations using the linearization of a relevant elliptic operator. The construction can be used to provide model Higgs bundles in all the 2g−3 exce…
ASK-NN detects distribution drifts in LLM-generated text.
problem Hallucinations and artificial text in LLM-generated outputs.
method Asymmetric two-sample test based on directed k-nearest-neighbor graph.
result ASK-NN is competitive with baselines on various benchmarks.
Graph-based multi-label classifier extends CULP for multi-label data.
problem Solving multi-label classification problems.
method Extends CULP algorithm to handle multi-label data.
result Competitive results compared to cutting-edge multi-label classifiers.
Strict plurisubharmonicity proven for Teichmüller energy on Hitchin representations.
problem Proving strict plurisubharmonicity of Teichmüller energy for Hitchin representations.
method Analyzing energy functional E on Teichmüller space associated to Hitchin representations. result Strict plurisubharmonicity of energy functional E proven. Clustering consists of grouping together samples giving their similar properties. The problem of modeling simultaneously groups of samples and features is known as Co-Clustering. This paper introduces ROCCO - a Robust Continuous Co-Clustering algorithm. ROCCO is a scalable, hyperparameter-free, easy and ready to use al…
New text as data techniques offer a great promise: the ability to inductively discover measures that are useful for testing social science theories of interest from large collections of text. We introduce a conceptual framework for making causal inferences with discovered measures as a treatment or outcome. Our framewo…
Framework improves clinical timeline reconstruction from text and tables.
problem Temporal precision and event timing in clinical narratives and EHRs.
method Retrieval-augmented multimodal alignment framework.
result Consistently improves absolute timestamp accuracy and temporal concordance.
Proposes a method to adapt labels on graphs with few labeled nodes.
problem Domain adaptation for graphs with limited labeled nodes.
method Optimization problem solving label transfer using spectral graph wavelets.
result Method yields satisfactory classification accuracy compared to existing methods.
Generates missing node attributes for better graph-based tasks.
problem Missing or incomplete node attributes degrade graph-based algorithms' performance.
method Deep adversarial learning-based method (NANG) to generate node attributes.
result Generated node attributes improve node classification and link prediction.
A new framework uses text descriptions to improve protein design.
problem Lack of effective methods to incorporate textual descriptions in protein design.
method ProteinDT framework that combines text and protein structural information.
result ProteinDT significantly improves protein design accuracy and performance.
BERT-based word embeddings improve active learning for text datasets.
problem Efficiently labelling large text datasets for machine learning.
method Evaluation of text representation mechanisms (BERT vs. bag of words) in active learning.
result BERT-based word embeddings significantly improve active learning performance.
Visual question answering is a recently proposed artificial intelligence task that requires a deep understanding of both images and texts. In deep learning, images are typically modeled through convolutional neural networks, and texts are typically modeled through recurrent neural networks. While the requirement for mo…
LFD method improves text classification by making features clearer and less label-leaking.
problem Creating interpretable text representations that are both predictive and understandable.
method LFD method: proposes lexical and semantic features from contrastive text pairs, screens candidates using κ, and selects features by residual gain. result LFD features achieve higher human-human and human-LLM agreement than baseline concepts and are less label-leaking.
PGRec improves recommendation by modeling user-item preferences as a graph and embedding it for better predictions.
problem Sparse user-item data in recommender systems.
method PGRec models user-item preferences as a PrefGraph, then uses deep learning and factorization to embed and predict user preferences.
result PGRec outperforms state-of-the-art methods by up to 3.2% in NDCG@10.
Enhances GNNs with text features for better fake news detection.
problem Detecting disinformation on social media using GNNs.
method Integrates Transformer-based textual features into GNNs.
result Contextual text representations improve GNN performance by 33.8% in Macro F1.
The paper studies mapping class group actions on character varieties of surfaces.
problem Understanding the dynamics of mapping class group actions on relative extPSL(2,R)-character varieties. method Definition and proof of simple-stability and primitive-stability of representations.
result Holonomies of hyperbolic cone surfaces are simple-stable and primitive-stable.
Paper develops heavy-tailed embeddings for better text classification and augmentation.
problem Improving text classification, especially for extreme values.
method Develops heavy-tailed embeddings using multivariate extreme value theory and introduces a scale-invariant classifier.
result The classifier outperforms baselines and generates meaningful augmented text.
Autoencoders have been successful in learning meaningful representations from image datasets. However, their performance on text datasets has not been widely studied. Traditional autoencoders tend to learn possibly trivial representations of text documents due to their confounding properties such as high-dimensionality…