Study various topologies on polynomial knots and their homotopy types.
problem Understanding different topologies on polynomial knots and their impact on homotopy types.
method Examined spaces of polynomial knots in Rn with various topologies and studied their homotopy types. result The homotopy type of the space of polynomial knots in R3 is S2. Proposes a topological framework to study modular invariants and related concepts.
problem Exploring modular invariants and related concepts in topological quantum field theory.
method Topological paradigm in alterfold topological quantum field theory.
result Establishes a novel integral identity for modular invariance across multiple Morita contexts.
If p:Y→X is an unramified covering map between two compact oriented surfaces of genus at least two, then it is proved that the embedding map, corresponding to p, from the Teichmüller space T(X), for X, to T(Y) actually extends to an embedding between the Thurston compactification of the tw…
Enhances MIL performance in scarce data scenarios using topological inductive biases.
problem Low performance of MIL in data-scarce scenarios.
method Incorporates topological inductive biases into MIL framework.
result Average performance improvements of 15.3% for synthetic datasets, 2.8% for benchmarks, and 5.5% for rare anemia classification.
Proposes a method to forecast spatial-temporal data with limited training data.
problem Forecasting with nodes having no temporal training data.
method Temporal data augmentation and spatial graph topology learning.
result Improves forecasting performance on nodes without training data.
The learnability of different neural architectures can be characterized directly by computable measures of data complexity. In this paper, we reframe the problem of architecture selection as understanding how data determines the most expressive and generalizable architectures suited to that data, beyond inductive bias.…
Enhances graph neural networks with structural message-passing for better generalization.
problem Limited representation power and inability to learn basic graph topological properties.
method Proposes a framework that includes a one-hot encoding of nodes and parametrized message and update functions ensuring permutation equivariance.
result Achieves state-of-the-art results on molecular graph regression on the ZINC dataset.
TGAT learns node embeddings for evolving graphs, capturing both static and temporal features.
problem Learning node embeddings for dynamic graphs with evolving topological structures and temporal patterns.
method Temporal Graph Attention (TGAT) layer using self-attention and functional time encoding.
result TGAT model can inductively infer node embeddings for new and observed nodes as the graph evolves.
Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversari…
In this paper we study the topology of three different kinds of spaces associated to polynomial knots of degree at most d, for d≥2. We denote these spaces by Od, Pd and Qd. For d≥3, we show that the spaces Od and Pd are path connected and the …
Paper explores how knowledge distillation transfers inductive biases between models.
problem Transferring inductive biases between models for tasks with limited data.
method Knowledge distillation applied to models with different inductive biases (LSTMs vs. Transformers, CNNs vs. MLPs).
result Effect of inductive biases is transferred through knowledge distillation, impacting both performance and solution characteristics.
Differential chains are a proper subspace of de Rham currents given as an inductive limit of Banach spaces endowed with a geometrically defined strong topology. Boundary is a continuous operator, as are operators that dualize to Hodge star, Lie derivative, pullback and interior product. Partitions of unity exist in thi…
Dror Bar-Natan and Ofer Ron have questioned the accuracy of the statement on page 453, line 2 minus of my paper "Groups of Ribbon Knots", Topology Vol 37, No. 2, 441-458, that "It follows from the inductive proof that Rn is of index 2." See their article posted on arXiv: math.GT/0309282. We give here full deta…
New proof shows exotic 4-manifolds exist without complex calculations.
problem Existence of exotic 4-manifolds in topology.
method Used Beliakova and Wehrli's s-invariant for links in S3 and Stošić's induction scheme to simplify computations. result Existence of exotic compact, orientable 4-manifolds proven without skein lasagna modules.
The present paper describes a way to relate Martin boundaries on spaces of varying topology. This enables us to approach some detailed inductive analysis of the eigenfunctions of conformal Laplacians on minimal hypersurfaces near their singularities. This can directly be used resp. translated to understand the way how …
I-BERT extends Transformer's self-attention to arbitrary input lengths.
problem Transformer models struggle with inductive generalization to unseen input lengths.
method Replaces positional encodings with a recurrent layer.
result I-BERT achieves state-of-the-art results on algorithmic tasks.
New method quantifies inductive bias for machine learning tasks.
problem Quantifying the amount of inductive bias in machine learning models.
method Estimates inductive bias by modeling loss distribution of random hypotheses.
result Higher dimensional tasks require greater inductive bias.
Proves left-orderability of mapping class groups of infinite-type surfaces.
problem Left-orderability of mapping class groups of infinite-type surfaces.
method Inductive construction of a stable Alexander system and ideal arc systems.
result Proves left-orderability using carefully chosen exhaustion by finite-type subsurfaces.
Equivalence proven between two torsion invariants for flat vector bundles.
problem Equivalence of Igusa-Klein and Bismut-Lott torsion invariants for flat vector bundles.
method Reduction to trivial flat line bundles using Artin's induction theorem.
result Igusa-Klein and Bismut-Lott torsion invariants are equivalent for flat vector bundles with finite holonomy.
The paper extends Gaussian processes to model complex interactions in cellular complexes.
problem Capturing topological inductive biases in machine learning models.
method Proposes Gaussian processes on cellular complexes, introducing novel kernels.
result Derives two novel kernels for modeling interactions between cells.
Transformers tend to learn more symmetric functions in sequence data.
problem Understanding inductive bias in Transformers with infinitely over-parameterized models.
method Analyzing Transformers in the Gaussian process limit, using representation theory of the symmetric group.
result Transformers are biased towards more permutation symmetric functions, and this can be quantitatively predicted.
GraIL predicts relations by reasoning over subgraphs, outperforming embeddings.
problem Relation prediction in knowledge graphs using latent representations is limited.
method Graph neural network with inductive bias to learn entity-independent relational semantics.
result GraIL outperforms existing rule-induction baselines in the inductive setting.
Ensemble method detects time series anomalies without preselecting parameter values.
problem Anomaly detection requires known anomaly length, limiting practicality.
method Ensemble grammar induction for variable-length anomalies.
result Ensemble approach outperforms existing methods with different parameter selections.
Transformers learn rich in-context dependencies efficiently.
problem Understanding how transformers learn long-range dependencies efficiently.
method Approximation and dynamics analysis of induction head mechanisms.
result Abrupt transition from lazy to rich mechanisms during training.
In this paper, we examine previous work on the naive Bayesian classifier and review its limitations, which include a sensitivity to correlated features. We respond to this problem by embedding the naive Bayesian induction scheme within an algorithm that c arries out a greedy search through the space of features. We hyp…
This article presents GuideR, a user-guided rule induction algorithm, which overcomes the largest limitation of the existing methods-the lack of the possibility to introduce user's preferences or domain knowledge to the rule learning process. Automatic selection of attributes and attribute ranges often leads to the sit…
Novel approach trains LLMs for inductive reasoning using probabilistic programs.
problem Training LLMs for inductive reasoning with sparse, ambiguous data.
method Program-based Posterior Training (PPT) using probabilistic inference.
result Significant improvement in estimation accuracy and alignment with human judgments.
Study reveals biases in gradient descent for GLNs, improving neural network performance.
problem Understanding and improving the inductive biases of deep neural networks.
method Derive infinite-time training limit of gated linear networks and generalize to other networks.
result Theoretical framework captures key inductive biases of ReLU networks.
CSA improves recommender systems by learning context-aware feature representations.
problem Limited expressiveness of traditional IMC methods for feature representations.
method Generalizes self-attention mechanism to IMC, learning context-aware feature representations.
result Extensive experiments show CSA's effectiveness on real RS datasets.
Mobile gaming has emerged as a promising market with billion-dollar revenues. A variety of mobile game platforms and services have been developed around the world. One critical challenge for these platforms and services is to understand user churn behavior in mobile games. Accurate churn prediction will benefit many st…
GTEA learns node representations in temporal interaction graphs.
problem Inductive representation learning on temporal interaction graphs.
method Integrates sequence model with time encoder and self-attention scheme for edge and node embeddings.
result GTEA learns comprehensive node representations capturing temporal and structural characteristics.
Proves formula for 3D index change with Dehn filling.
problem Transforming 3D index under Dehn filling.
method Relative 3D index, gluing principle, inductive framework, q-hypergeometric functions.
result Rigorous proof of Gang-Yonekura formula.
Study explores efficient data division for ICPs.
problem Efficiently dividing limited development data for ICPs.
method Experiments with training, calibration, and test data divisions.
result Allows overlap between training and calibration sets improves efficiency.
Inductive graph-based approach for disease classification with incomplete data.
problem Classifying patients with incomplete multi-modal data.
method Multi-modal graph fusion trained end-to-end for node-level classification.
result Outperforms single static graph approach in multi-modal disease classification.
We study the topological and differentiable singularities of the configuration space C(Γ) of a mechanical linkage Γin d-dimensional Euclidean space, defining an inductive sufficient condition to determine when a configuration is singular. We show that this condition holds for generic singularities, provide a mechanical…
We construct infinite sequences of pseudo-Anosov homeomorphisms without fixed points and leaving invariant a sequence of orientable measured foliations on the same topological surface and the same stratum of the space of abelian differentials. The existence of such sequences show that all pseudo-Anosov homeomorphisms f…
In an earlier paper [Acta Mathematica, v. 176, 1996, 145-169, alg-geom/9505024 ] the present authors and Dennis Sullivan constructed the universal direct system of the classical Teichmüller spaces of Riemann surfaces of varying genus. The direct limit, which we called the universal commensurability Teichmüller space, $…
Paper summarizes unsupervised learning challenges for disentangled representations.
problem Unsupervised learning of disentangled representations without inductive biases.
method Theoretical and practical analysis of existing approaches.
result Unsupervised disentanglement is fundamentally impossible without inductive biases.
Paper compares AutoML methods for recommending classification algorithms.
problem Finding the best classification algorithm for a dataset.
method Four AutoML methods using Evolutionary Algorithms and CASH approach.
result EA-based methods, especially decision-tree induction, produce interpretable models.
RPPs improve deep learning models with soft equivariance constraints.
problem Balancing expressiveness and inductive biases in deep learning.
method Introducing Residual Pathway Priors (RPPs) to convert hard constraints into soft priors.
result RPPs enable models to learn structured solutions while retaining flexibility.
The paper presents a new method to represent directed graphs using pseudo-Riemannian manifolds.
problem Representing directed graphs in a compact and meaningful way.
method Combines pseudo-Riemannian metric structure, non-trivial global topology, and a unique likelihood function.
result Low-dimensional cylindrical Minkowski and anti-de Sitter spacetimes produce equal or better graph representations than curved Riemannian manifolds.
DILP improves fraud detection explainability without significant performance boost.
problem Improving fraud detection explainability in machine learning.
method Differentiable Inductive Logic Programming (DILP) for fraud detection with data curation.
result DILP provides comparable results to traditional methods but lacks significant advantage.
The paper solves circle packings on surfaces with boundaries.
problem Circle packing on surfaces with boundaries and finite genus.
method Using Thurston's algorithm and discrete Schwarz-Pick lemma.
result A unique solution to the boundary value problem exists.
A new method for graph-structured data improves transformer performance by incorporating topology.
problem Improving transformer performance on graph-structured data.
method Parameterizing topological masks as a learnable function of a weighted adjacency matrix, approximated with graph random features.
result Efficient masking algorithms provide strong performance gains for tasks on image and point cloud data.
Interpolated-MLPs control inductive bias for better performance in low-compute tasks.
problem Low-compute performance gap between MLPs and CNNs.
method Introduced Interpolated MLP (I-MLP) approach to control inductive bias incrementally.
result Continuous logarithmic relationship between inductive bias and performance in low-compute tasks.
Ends and cohomology theory for noncompact spaces.
problem Study of noncompact spaces and their invariants.
method Exposition of ends theory, introduction of reduced end cohomology, proof of theorems.
result Proof of a theorem on end cohomology of end sums of manifolds.
Autostackability for finitely generated groups is defined via a topological property of the associated Cayley graph which can be encoded in a finite state automaton. Autostackable groups have solvable word problem and an effective inductive procedure for constructing van Kampen diagrams with respect to a canonical fini…
This paper explores the limits of Transformers in learning new patterns from scratch.
problem Understanding when Transformers can learn new patterns from scratch.
method Introducing the 'globality degree' to measure learnability and developing scratchpad techniques.
result Distributions with high globality cannot be learned efficiently by Transformers.