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.
A new method learns graph distributions invariant to node ordering.
Variational inference struggles with weight symmetries in neural networks, leading to biased posteriors.
Generative model for set-valued data using permutation invariant flows.
ABI adapts to graph data for fast, scalable inference.
MEM learns set functions from permutation-invariant data.
Neural networks learn from ensemble forecasts without considering their order.
New LCM aggregator improves GNN performance and efficiency.
This work improves multi-modal generative models by using permutation-invariant neural networks.
New research limits what GNNs can compute and generalizes their performance.
New algorithm uses GNNs to optimize rewards in graph-structured data.
HistNetQ improves quantification tasks by optimizing loss functions and eliminating label requirements.
Paper develops deep neural networks for wireless tasks with reduced complexity.
We propose a permutation-invariant loss function designed for the neural networks reconstructing a set of elements without considering the order within its vector representation. Unlike popular approaches for encoding and decoding a set, our work does not rely on a carefully engineered network topology nor by any addit…
A new complexity measure for neural networks improves upon classical methods.
Survey on neural networks for set-based data.
Permutation invariant network learns Wasserstein metrics.
In this paper, we develop a theory about the relationship between -invariant/equivariant functions and deep neural networks for finite group . Especially, for a given -invariant/equivariant function, we construct its universal approximator by deep neural network whose layers equip -actions and each affine t…
Unordered feature sets are a nonstandard data structure that traditional neural networks are incapable of addressing in a principled manner. Providing a concatenation of features in an arbitrary order may lead to the learning of spurious patterns or biases that do not actually exist. Another complication is introduced …
A new DNN structure reduces complexity for wireless tasks.
DDEQs extend DEQs to discrete measure inputs using Wasserstein gradient flows.
LMC loss barrier decreases to zero with large network width.
Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set, models used to address them should be permutation invariant. We present an attenti…
We introduce graph normalizing flows: a new, reversible graph neural network model for prediction and generation. On supervised tasks, graph normalizing flows perform similarly to message passing neural networks, but at a significantly reduced memory footprint, allowing them to scale to larger graphs. In the unsupervis…
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on the Ladder network proposed by Valpola (…
Regularizes RNNs to be invariant to input order.
This paper focuses on the discrimination capacity of aggregation functions: these are the permutation invariant functions used by graph neural networks to combine the features of nodes. Realizing that the most powerful aggregation functions suffer from a dimensionality curse, we consider a restricted setting. In partic…
We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label. We use a deep lattice network model so we can architect the model structure to enhance interpretability, and add monotonicity constraints between inputs-and-outputs.…
New neural network models learn symmetric functions of varying input sizes.
Proposes a few-shot learning method for feature selection without labeled data.
The computer-aided analysis of medical scans is a longstanding goal in the medical imaging field. Currently, deep learning has became a dominant methodology for supporting pathologists and radiologist. Deep learning algorithms have been successfully applied to digital pathology and radiology, nevertheless, there are st…
Neural processes (NPs) learn stochastic processes and predict the distribution of target output adaptively conditioned on a context set of observed input-output pairs. Furthermore, Attentive Neural Process (ANP) improved the prediction accuracy of NPs by incorporating attention mechanism among contexts and targets. In …
Invariant polynomials improve machine learning performance.
While there are optimal TSP solvers, as well as recent learning-based approaches, the generalization of the TSP to the Multiple Traveling Salesmen Problem is much less studied. Here, we design a neural network solution that treats the salesmen, cities and depot as three different sets of varying cardinalities. We apply…
EquivCNP learns group symmetries for conditional data.
Single-microphone, speaker-independent speech separation is normally performed through two steps: (i) separating the specific speech sources, and (ii) determining the best output-label assignment to find the separation error. The second step is the main obstacle in training neural networks for speech separation. Recent…
PARD generates graphs efficiently and invariantly to node ordering.
Multiple instance learning (MIL) is a variation of supervised learning where a single class label is assigned to a bag of instances. In this paper, we state the MIL problem as learning the Bernoulli distribution of the bag label where the bag label probability is fully parameterized by neural networks. Furthermore, we …
Neural point estimators improve parameter estimation from replicated data.
In this work we propose a new neural network architecture that efficiently implements and learns general purpose set-equivariant functions. Such a function f maps a set of entities x = {x1, . . . , xn} from one domain to a set of same cardinality y = f (x) = {y1, . . . , yn} in another domain regardless of the ordering…
The introduction of convolutional layers greatly advanced the performance of neural networks on image tasks due to innately capturing a way of encoding and learning translation-invariant operations, matching one of the underlying symmetries of the image domain. In comparison, there are a number of problems in which the…
SRN improves set representations for relational reasoning.
Proposes FMS for more efficient neural network hyperparameter optimization.
Geom-GCN improves graph neural networks by preserving structural information and capturing long-range dependencies.
New translation equivariant neural processes improve spatio-temporal data modeling.
Generating point clouds, e.g., molecular structures, in arbitrary rotations, translations, and enumerations remains a challenging task. Meanwhile, neural networks utilizing symmetry invariant layers have been shown to be able to optimize their training objective in a data-efficient way. In this spirit, we present an ar…
Validates conformal prediction for network data under non-uniform sampling.
Improves modeling of sets with permutation invariant densities.
Generative models of graph structure have applications in biology and social sciences. The state of the art is GraphRNN, which decomposes the graph generation process into a series of sequential steps. While effective for modest sizes, it loses its permutation invariance for larger graphs. Instead, we present a permuta…