Existing relation classification methods that rely on distant supervision assume that a bag of sentences mentioning an entity pair are all describing a relation for the entity pair. Such methods, performing classification at the bag level, cannot identify the mapping between a relation and a sentence, and largely suffe…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,694 papers · 148 categories
Trend · papers per month
48 results for “relation classification”
Framework for few-shot relation classification with minimal training data.
problem Few-shot relation classification with limited training data.
method Meta-learning framework that combines instance and support knowledge.
result Framework outperforms state-of-the-art results and achieves competitive performance with large training data.
Relational learning deals with data that are characterized by relational structures. An important task is collective classification, which is to jointly classify networked objects. While it holds a great promise to produce a better accuracy than non-collective classifiers, collective classification is computational cha…
We present a Few-Shot Relation Classification Dataset (FewRel), consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers. The relation of each sentence is first recognized by distant supervision methods, and then filtered by crowdworkers. We adapt the most recent state-of-th…
In many supervised learning tasks, the entities to be labeled are related to each other in complex ways and their labels are not independent. For example, in hypertext classification, the labels of linked pages are highly correlated. A standard approach is to classify each entity independently, ignoring the correlation…
This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutiona…
Temporal networks are ubiquitous and evolve over time by the addition, deletion, and changing of links, nodes, and attributes. Although many relational datasets contain temporal information, the majority of existing techniques in relational learning focus on static snapshots and ignore the temporal dynamics. We propose…
This paper presents a novel latent variable recurrent neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences. A recurrent neural network generates individual words, thus reaping the benefits of discriminatively-trained vector representati…
Study shows pre-trained models can handle long-tailed relations well, improving classifier performance.
problem Challenges in long-tailed relation classification due to class imbalance.
method Used instance-balanced sampling to pre-train models and then improved classifier performance through attentive relation routing.
result Robust classifier with attentive relation routing achieves better long-tailed classification ability.
Graphs from features improve classification accuracy in tasks.
problem Traditional classification tasks can be improved by incorporating relational information.
method Construct geometric graphs from features and use them in Graph Convolutional Networks.
result Graphs derived from features increase classification accuracy and improve class separation.
In this paper, we present the classification of generalized Wallach spaces and discuss some related problems.
Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another …
Multi-label network classification is a well-known task that is being used in a wide variety of web-based and non-web-based domains. It can be formalized as a multi-relational learning task for predicting nodes labels based on their relations within the network. In sparse networks, this prediction task can be very chal…
L. Paoluzzi constructed a family of compact orientable three-dimensional hyperbolic manifolds with totally geodesic boundary, which were, by construction, closely related to the three-dimensional torus. This paper gives their complete classification up to isometry, and also their isometry groups. The key tool is the so…
The paper deals with the program of determining the complexity of various homeomorphism relations. The homeomorphism relation on compact Polish spaces is known to be reducible to an orbit equivalence relation of a continuous Polish group action (Kechris-Solecki). It is shown that this result extends to locally compact …
This paper proposes Relational Similarity Machines (RSM): a fast, accurate, and flexible relational learning framework for supervised and semi-supervised learning tasks. Despite the importance of relational learning, most existing methods are hard to adapt to different settings, due to issues with efficiency, scalabili…
Can we learn a binary classifier from only positive data, without any negative data or unlabeled data? We show that if one can equip positive data with confidence (positive-confidence), one can successfully learn a binary classifier, which we name positive-confidence (Pconf) classification. Our work is related to one-c…
Study maximal antipodal sets in exceptional symmetric spaces.
problem Classify maximal antipodal sets in exceptional symmetric spaces.
method Combining existing literature and new results, classify maximal antipodal sets.
result Complete classification of maximal antipodal sets in all exceptional compact symmetric spaces.
We define an order relation among oriented -complexes. We show that with respect to this relation, two -complexes over the same complex are homotopy equivalent if and only if there is an isometry between the second homology groups. We also consider minimal objects of this relation.
New classification of complex hypersurfaces in 3D.
problem Classifying simply-transitive Levi non-degenerate hypersurfaces in .
method Novel Lie algebraic approach, new coordinate-free formula for quartic tensor.
result Unique non-tubular model with geometric relations to planar equi-affine geometry.
We present a local classification of smooth projective surfaces in 3-space via projective transformations in accordance with singularity types of central projections up to codimension 4. We also discuss relations between our classification of Monge forms and bifurcations of parabolic curves and flecnodal curves.
In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover …
Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undirected graphs. Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated wi…
Study on 4D Lie groups and related almost hypercomplex manifolds.
problem Characterizing almost hypercomplex manifolds with specific metrics.
method Construction and classification of manifolds based on Lie algebras.
result Established a connection between Lie algebra classes and manifold classifications.
Using the classification of transitive groups we classify indecomposable quandles of size <36. This classification is available in Rig, a GAP package for computations related to racks and quandles. As an application, the list of all indecomposable quandles of size <36 not of type D is computed.
Paper shows similarity learning can lead to strong binary classification performance.
problem How similarity learning can lead to good classification performance.
method Product-type formulation of similarity learning is connected to binary classification through an excess risk bound.
result Similarity learning can directly elicit a decision boundary for binary classification.
Many classification problems involve data instances that are interlinked with each other, such as webpages connected by hyperlinks. Techniques for "collective classification" (CC) often increase accuracy for such data graphs, but usually require a fully-labeled training graph. In contrast, we examine how to improve the…
Paper explores connections between loss functions and consistency in binary classification and regression.
problem Consistency in binary classification and regression applications.
method Characterization of conformable loss functions and derivation of a new Huber-type loss function.
result Margin-based loss functions are equivalent to loss functions of squared standardized logistic regression residuals.
A pass-move and a $#$-move are local moves on oriented links defined by L.H. Kauffman and H. Murakami respectively. Two links are self pass-equivalent (resp. self $#$-equivalent) if one can be deformed into the other by pass-moves (resp. $#$-moves), where non of them can occur between distinct components of the link. T…
The paper classifies symmetric triads with multiplicities and their applications.
problem Classifying symmetric triads with multiplicities and their applications.
method Developed the theory of symmetric triads with multiplicities, classified abstract triads, and determined corresponding triads for commutative compact triads.
result Classified symmetric triads with multiplicities and their applications.
We propose a general approach to modeling semi-supervised learning (SSL) algorithms. Specifically, we present a declarative language for modeling both traditional supervised classification tasks and many SSL heuristics, including both well-known heuristics such as co-training and novel domain-specific heuristics. In ad…
We introduce a conceptually simple and effective method to quantify the similarity between relations in knowledge bases. Specifically, our approach is based on the divergence between the conditional probability distributions over entity pairs. In this paper, these distributions are parameterized by a very simple neural…
I apply the algebraic classification of self-adjoint endomorphisms of provided by their Jordan canonical form to the Ricci curvature tensor of four-dimensional neutral manifolds and relate this classification to an algebraic classification of the Ricci curvature spinor. These results parallel similar re…
Estimating a constrained relation is a fundamental problem in machine learning. Special cases are classification (the problem of estimating a map from a set of to-be-classified elements to a set of labels), clustering (the problem of estimating an equivalence relation on a set) and ranking (the problem of estimating a …
32 knot projections classified based on forbidden Reidemeister moves.
problem Classifying knot projections based on allowed Reidemeister moves.
method 32 homotopy classifications based on forbidden Reidemeister moves.
result 20 non-trivial cases of knot projections are mutually different.
The study classifies Heintze groups up to isometry and quasi-isometry in low dimensions.
problem Classifying Heintze groups up to isometry and quasi-isometry in low dimensions.
method Analyzing quasi-isometries and isometries of Heintze groups, applying existing tools to groups of dimension 4 and 5.
result Complete classification of simply connected solvable groups in dimension 4 and groups of polynomial growth in dimension 5 up to isometry.
We classify all rotational surfaces in Euclidean space whose principal curvatures and satisfy the linear relation , where and are two constants. We give a variational characterization of these surfaces in terms of its generating curve. As a consequence of our classification, we find clos…
Graph-based approach predicts stock trends using dynamic multi-relational graphs.
problem Predicting future stock movements in complex, time-evolving stock relationships.
method Dynamic multi-relational stock graphs, stochastic diffusion process, parallel retention.
result Outperforms state-of-the-art baselines in stock trend forecasting.
We investigate graph neural networks for multi-relational data.
problem Understanding and improving graph neural networks for multi-relational data.
method Aligning Relational GCN and Compositional GCN with the Weisfeiler-Leman test to understand their expressive power and introduce a new -RN architecture.
result The -RN architecture overcomes the expressiveness limitations of Relational GCN and Compositional GCN.
TransINT embeds KGs by preserving implication rules, outperforming existing methods.
problem Embedding KGs while preserving relation implications for better access and analysis.
method Isomorphic intersections of linear subspaces with shared parameters for missing facts.
result Significant performance improvement in link prediction and triple classification.
We study vector fields of the plane preserving the form of Liouville. We present their local models up to the natural equivalence relation, and describe local bifurcations of low codimension. To achieve that, a classification of univariate functions is given, according to a relation stricter than contact equivalence. W…
New method estimates Nishimori temperature for node classification in weighted graphs.
problem Estimating Nishimori temperature for Bayesian inference.
method Spectral method using eigenvalues of Bethe Hessian matrix.
result Spectral method outperforms existing approaches in node classification.
The paper reviews and extends calibration concepts for classification and regression.
problem Formalizing compatibility between probabilistic predictions and outcomes.
method Review and extension of existing calibration concepts, introduction of new concepts.
result Hierarchical relations between calibration concepts for various data types.
We examine two fundamental tasks associated with graph representation learning: link prediction and semi-supervised node classification. We present a novel autoencoder architecture capable of learning a joint representation of both local graph structure and available node features for the multi-task learning of link pr…
In this article, relations between the root space decomposition of a Riemannian symmetric space of compact type and the root space decompositions of its totally geodesic submanifolds (symmetric subspaces) are described. These relations provide an approach to the classification of totally geodesic submanifolds in Rieman…
Knowledge graphs enable a wide variety of applications, including question answering and information retrieval. Despite the great effort invested in their creation and maintenance, even the largest (e.g., Yago, DBPedia or Wikidata) remain incomplete. We introduce Relational Graph Convolutional Networks (R-GCNs) and app…
The paper finds symplectic mapping class relations using pencil pairs.
problem Understanding symplectic mapping class relations in 4-manifolds.
method Applying classification results for Fano 3-folds and polarized K3 surfaces to a general methodology of finding pencil pairs.
result Symplectic mapping class relations between products of positive Dehn twists.
New method for learning on heterogeneous graphs without meta-paths.
problem Learning on heterogeneous graphs is sensitive to meta-paths choice, leading to poor performance.
method Decompose heterogeneous graph into homogeneous relation-type graphs, combine higher-order representations, use attention mechanisms.
result Our model outperforms state-of-the-art baselines in vertex classification tasks on heterogeneous graph datasets.