Network embedding converts network data into vectors for machine learning.
problem Machine learning tasks on networks require vector representations of nodes and links.
method Various unsupervised and supervised methods for converting network data into vectors.
result Network embedding methods aim to preserve network structure in learned feature representations.
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.
The recent proliferation of publicly available graph-structured data has sparked an interest in machine learning algorithms for graph data. Since most traditional machine learning algorithms assume data to be tabular, embedding algorithms for mapping graph data to real-valued vector spaces has become an active area of …
The paper explores theories behind graph and relational data vector embeddings.
problem Understanding the foundations of vector embeddings for graphs and relational structures.
method Proposes two theoretical approaches to understand vector embeddings.
result Draws connections between various embedding techniques and suggests future research directions.
Graph embedding methods produce unsupervised node features from graphs that can then be used for a variety of machine learning tasks. Modern graphs, particularly in industrial applications, contain billions of nodes and trillions of edges, which exceeds the capability of existing embedding systems. We present PyTorch-B…
We develop computationally efficient Riemannian manifolds for graph embeddings.
problem Challenging to maintain computational tractability in non-Euclidean graph embeddings.
method Explore computationally efficient matrix manifolds for graph embeddings.
result Consistent improvements over Euclidean geometry and outperforming hyperbolic and elliptical embeddings.
Byte-level machine translation outperforms embedding-based methods.
problem Improving machine translation without embedding layers.
method Replacing embedding layers with one-hot representations of bytes, and using decoder-input dropout.
result Byte-to-byte machine translation achieves BLEU scores comparable to character-level and subword-level models.
Network embedding helps predict speed limits on incomplete Danish road network.
problem Incomplete speed limit data on Danish roads limits machine learning applications.
method Applied node2vec network embedding to Danish road network.
result Network embedding can derive useful features for predicting speed limits.
Embedding-based Knowledge Base Completion models have so far mostly combined distributed representations of individual entities or relations to compute truth scores of missing links. Facts can however also be represented using pairwise embeddings, i.e. embeddings for pairs of entities and relations. In this paper we ex…
WEGL embeds graphs in a vector space for faster machine learning.
problem Efficiently embedding graphs for machine learning tasks.
method Wasserstein distance for node embedding similarity, Monge maps for graph representation.
result State-of-the-art classification performance with superior computational efficiency.
Embeddings are ubiquitous in machine learning, appearing in recommender systems, NLP, and many other applications. Researchers and developers often need to explore the properties of a specific embedding, and one way to analyze embeddings is to visualize them. We present the Embedding Projector, a tool for interactive v…
Paper provides conditions for reliable use of pre-trained embeddings in econometrics.
problem Uncertainty in using pre-trained embeddings for econometric tasks.
method Derives sufficient conditions and convergence rates for machine learning models with pre-trained embeddings.
result Establishes theoretical foundations for reliable use of pre-trained embeddings in econometrics.
DeBayes uses Bayesian methods to create fair network embeddings.
problem Ensuring fairness in network embeddings for high-impact applications.
method Bayesian approach to learn debiased network embeddings.
result DeBayes produces fairer network embeddings for link prediction.
News embeddings improve volatility forecasts.
problem Improving volatility forecasting accuracy.
method Transformed news text into embeddings, evaluated standalone and combined with benchmarks.
result News contains useful predictive information, especially for stock-related content.
Machine learning maps knots to embeddings, revealing topological invariants.
problem Learning topological invariance in knot theory.
method Contrastive and generative machine learning techniques, auto-regressive decoder Transformer network.
result Neural networks can map different knots to the same point in an embedding vector space.
Efficiently computes embeddings for large graphs using coarsening.
problem Inefficient computation of graph embeddings for large-scale graphs.
method Graph coarsening based on Schur complements and Gaussian elimination.
result Efficiently computed embeddings on coarsened graph match Schur complement embeddings in expectation.
This paper connects functional data analysis with machine learning techniques.
problem Lack of theoretical analysis for functional depths.
method Viewing functional depths as kernel mean embeddings in machine learning.
result Facilitates answers to open questions about functional depths.
Complex embeddings handle non-metric proximity data better than traditional methods.
problem Proximities not always metric or inner product-based, causing convergence issues.
method Proposes complex-valued embeddings for non-vectorial data.
result Complex embeddings outperform traditional techniques on benchmarks.
FastMap-D embeds directed graphs using potential fields.
problem Embedding directed graphs in Euclidean space.
method Generalization of FastMap to handle directed graphs using a potential field and machine learning.
result FastMap-D outperforms other approaches in embedding directed graphs.
Proposes FEFM and DeepFEFM for CTR prediction, outperforming state-of-the-art models.
problem Click-through rate prediction in online applications.
method Field-Embedded Factorization Machine (FEFM) and its deep counterpart DeepFEFM, combining feature embeddings and deep neural networks.
result FEFM and DeepFEFM outperform existing models in CTR prediction tasks.
Efficient neural networks for resource-constrained systems.
problem Reducing resource consumption in machine learning models for embedded systems.
method Quantized neural networks, network pruning, structural efficiency.
result Finding good trade-offs between resource efficiency and prediction quality is challenging.
We present a new approach for detecting related crime series, by unsupervised learning of the latent feature embeddings from narratives of crime record via the Gaussian-Bernoulli Restricted Boltzmann Machines (RBM). This is a drastically different approach from prior work on crime analysis, which typically considers on…
The paper uses news headlines to predict stock prices using embeddings.
problem Predicting stock prices using news headlines.
method Using OpenAI-based text embedding models and PCA to create vector encodings of news headlines, then training machine learning models on financial data.
result Headline data embeddings improve stock price prediction by at least 40%.
Proposes clustering as a new evaluation method for clinical knowledge embedding.
problem Traditional Link Prediction evaluation protocol loses information and harms model accuracy.
method Proposes Clustering Evaluation Protocol as an alternative.
result Experimental results show the proposed protocol can potentially replace Link Prediction.
New model uses financial news to predict stock returns.
problem Predicting stock returns based on financial news.
method Derive company embedding vectors from news, select basis assets, and use statistical methods.
result NEUS model outperforms Fama-French 5-factor model.
Paper explores understanding of neural source code embeddings.
problem Lack of understanding of contents and characteristics of code2vec embeddings.
method Small case study using code2vec embeddings to create binary SVM classifiers and compare performance with handcrafted features.
result Code2vec embeddings perform similarly to handcrafted features and have more evenly distributed information gains.
The web is loaded with textual content, and Natural Language Processing is a standout amongst the most vital fields in Machine Learning. But when data is huge simple Machine Learning algorithms are not able to handle it and that is when Deep Learning comes into play which based on Neural Networks. However since neural …
Word embeddings are a powerful approach for unsupervised analysis of language. Recently, Rudolph et al. (2016) developed exponential family embeddings, which cast word embeddings in a probabilistic framework. Here, we develop dynamic embeddings, building on exponential family embeddings to capture how the meanings of w…
Algorithm learns stock correlation matrix embedding using graph machine learning.
problem Understanding complex relationships among stocks based on their correlation matrix.
method Proposes a graph machine learning approach called Node2Vec to compress the correlation network into an embedding.
result The algorithm can learn an embedding from the correlation network of S&P 500 stock data.
A new method speeds up SoftMax normalization for embedding learning.
problem Efficiently learning distributed representations with SoftMax normalization.
method Proposes a linear-time heuristic approximation for mSoftMax(XYT), optimizing cross entropy. result Achieves higher or comparable accuracy to existing methods with lower computational time.
The paper explores how word embeddings affect the stability of downstream NLP models.
problem Small changes in training data can cause significant changes in model predictions.
method Empirical and theoretical analysis of embedding instability, including the introduction of eigenspace instability measure.
result Increasing embedding memory can reduce the disagreement in predictions by 5% to 37%.
The power of machine learning systems not only promises great technical progress, but risks societal harm. As a recent example, researchers have shown that popular word embedding algorithms exhibit stereotypical biases, such as gender bias. The widespread use of these algorithms in machine learning systems, from automa…
Paper proposes a matrix optimization model for reliable Euclidean embedding from noisy data.
problem Challenges in Euclidean embedding from noisy observations containing outliers.
method Matrix optimization based embedding model to detect and remove outliers.
result The model provides high accuracy estimators and successfully identifies outliers.
Networks are powerful data structures, but are challenging to work with for conventional machine learning methods. Network Embedding (NE) methods attempt to resolve this by learning vector representations for the nodes, for subsequent use in downstream machine learning tasks. Link Prediction (LP) is one such downstream…
Sommelier recommends machine learning algorithms for datasets based on scholarly knowledge.
problem Identifying the best machine learning algorithms for a dataset.
method Word embedding representations of scholarly knowledge to recommend algorithms.
result Sommelier's recommendations achieve on average 97.7% of optimal accuracy.
The success of machine learning methods heavily relies on having an appropriate representation for data at hand. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural information about data. However, recently there has been a surge in approaches that learn …
BC-Aligner maintains backward compatibility of embeddings after frequent updates.
problem Updating embeddings without requiring consumer teams to retrain their models.
method Learning backward compatible embeddings through BC-Aligner.
result BC-Aligner maintains backward compatibility with existing unintended tasks after multiple model version updates.
The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning and natural language processing tasks. We show that even word embeddings traine…
Obtaining continuous representations of structural data such as directed acyclic graphs (DAGs) has gained attention in machine learning and artificial intelligence. However, embedding complex DAGs in which both ancestors and descendants of nodes are exponentially increasing is difficult. Tackling in this problem, we de…
Combines BERT and graph CNN for improved text classification.
problem Text classification problems
method Combining BERT embedding and graph convolutional neural network
result Graph CNN model performs better than classical models combined with BERT
KEEN Universe provides reproducible and transferable knowledge graph embeddings.
problem Lack of reproducibility and transferability in KGE experiments.
method Developed an ecosystem with Python packages for reproducible and transferable KGEs.
result KEEN Universe facilitates sharing of trained KGE models across different fields.
Embedding graph nodes into a vector space can allow the use of machine learning to e.g. predict node classes, but the study of node embedding algorithms is immature compared to the natural language processing field because of a diverse nature of graphs. We examine the performance of node embedding algorithms with respe…
New method uses product embeddings to predict bundle success.
problem Designing effective product bundles in large retail settings.
method Leverage historical purchases and clickstream data to generate product embeddings, then use heuristics for complementarity and substitutability.
result Embeddings-based heuristics predict bundle success, robust across categories and retailers.
In recent years, there have been significant efforts on mitigating unethical demographic biases in machine learning methods. However, very little is done for kernel methods. In this paper, we propose a new fair kernel regression method via fair feature embedding (FKR-F2E) in kernel space. Motivated by prior works on…
Large-scale automated meta-analysis of neuroimaging data has recently established itself as an important tool in advancing our understanding of human brain function. This research has been pioneered by NeuroSynth, a database collecting both brain activation coordinates and associated text across a large cohort of neuro…
MAD framework learns operators from physics-embedded data efficiently.
problem Data-driven methods require costly labeled datasets and model-driven techniques face efficiency-accuracy trade-offs.
method Integrates physical laws with data-driven learning to generate physics-embedded analytical solutions and synthetic data.
result Eliminates dependence on experimental or simulated training data, enabling efficient operator learning across multi-parameter systems.
Interactive machine learning with weak supervision and pre-trained embeddings.
problem Training machine learning models with limited labeled data.
method Use pre-trained embeddings to define a distance function and extend source votes to nearby points.
result Significantly outperforms traditional weakly-supervised and fully-supervised methods.
Financial transactions can be considered edges in a heterogeneous graph between entities sending money and entities receiving money. For financial institutions, such a graph is likely large (with millions or billions of edges) while also sparsely connected. It becomes challenging to apply machine learning to such large…