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.
RESTA defends LLMs against jailbreaking attacks by adding random noise to embeddings.
Fishnets improve set and graph learning with scalable, robust aggregation.
Optimal Transport Graph Neural Networks (OT-GNN) improves graph embeddings by using optimal transport.
Proposes MamBO for efficient high-dimensional large-scale optimization.
Data aggregation improves HAC for resource-constrained systems.
We propose a dynamic neighborhood aggregation (DNA) procedure guided by (multi-head) attention for representation learning on graphs. In contrast to current graph neural networks which follow a simple neighborhood aggregation scheme, our DNA procedure allows for a selective and node-adaptive aggregation of neighboring …
New method for multi-modal depth prediction challenges.
Improves speaker verification for variable-duration utterances using a feature pyramid module.
STAG injects noise into graph neural networks to improve performance.
Optimal transport embedding learns feature sets efficiently.
Social recommendation has emerged to leverage social connections among users for predicting users' unknown preferences, which could alleviate the data sparsity issue in collaborative filtering based recommendation. Early approaches relied on utilizing each user's first-order social neighbors' interests for better user …
A new GNN model SPIN achieves state-of-the-art performance on diverse real-world datasets.
LATTE tackles heterogeneous network embedding challenges with layer-stacked attention.
Non-local GNNs improve performance on disassortative graphs.
GTEA learns node representations in temporal interaction graphs.
We present, GEM, the first heterogeneous graph neural network approach for detecting malicious accounts at Alipay, one of the world's leading mobile cashless payment platform. Our approach, inspired from a connected subgraph approach, adaptively learns discriminative embeddings from heterogeneous account-device graphs …
RR-GCN uses random transformations instead of learned weights for node embeddings.
The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant challenge in achieving accurate conversion from graph form …
SFBoW provides sentence embeddings with predefined dimensions.
Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. In this work, we present a Graph Convolutional Network (GCN) algorithm SWAG (Sample Weight and AGgregate), which combines efficient random walks and graph convolutions on weig…
New spectral clustering method for multi-layer networks improves accuracy.
In this paper, we focus on learning low-dimensional embeddings for nodes in graph-structured data. To achieve this, we propose Caps2NE -- a new unsupervised embedding model leveraging a network of two capsule layers. Caps2NE induces a routing process to aggregate feature vectors of context neighbors of a given target n…
We propose regression networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each class. In high dimensional embedding spaces the direction of data generally contains richer information than magnitude.…
Topic models are frequently used in machine learning owing to their high interpretability and modular structure. However, extending a topic model to include a supervisory signal, to incorporate pre-trained word embedding vectors and to include a nonlinear output function is not an easy task because one has to resort to…
Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent graph-structured data: losing the structural information of nodes in neighborhoo…
ComiRec framework predicts user interests for personalized recommendations.
Enhanced GNN with expanded attention window and partially random embeddings.
Dynamic assessment of patient status (e.g. by an automated, continuously updated assessment of outcome) in the Intensive Care Unit (ICU) is of paramount importance for early alerting, decision support and resource allocation. Extraction and cleaning of expert-selected clinical variables discards information and protrac…
EHNA learns node embeddings from historical network neighborhoods.
SANNE model generates embeddings for unseen nodes in graph networks.
Unsupervised method learns hierarchical graph representations without labels.
Graph Neural Networks (GNNs) are powerful to learn the representation of graph-structured data. Most of the GNNs use the message-passing scheme, where the embedding of a node is iteratively updated by aggregating the information of its neighbors. To achieve a better expressive capability of node influences, attention m…
Recommenders have become widely popular in recent years because of their broader applicability in many e-commerce applications. These applications rely on recommenders for generating advertisements for various offers or providing content recommendations. However, the quality of the generated recommendations depends on …
Proposes Gromov-Wasserstein methods for multi-view embedding.
A simple algorithm improves model generalization in expert advice settings.
In this paper, we propose a new pooling method called spatial pyramid encoding (SPE) to generate speaker embeddings for text-independent speaker verification. We first partition the output feature maps from a deep residual network (ResNet) into increasingly fine sub-regions and extract speaker embeddings from each sub-…
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 …
Recently, click-through rate (CTR) prediction models have evolved from shallow methods to deep neural networks. Most deep CTR models follow an Embedding\&MLP paradigm, that is, first mapping discrete id features, e.g. user visited items, into low dimensional vectors with an embedding module, then learn a multi-layer pe…
Method aggregates models with different hyper-parameters to adapt to target domain.
RGCF improves collaborative filtering by refining graph convolution embeddings.
Model-agnostic interpretation techniques allow us to explain the behavior of any predictive model. Due to different notations and terminology, it is difficult to see how they are related. A unified view on these methods has been missing. We present the generalized SIPA (sampling, intervention, prediction, aggregation) …
Proposes a novel node embedding framework for graphs using Fisher Information.
Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data. Based on the recent DeepSets architecture proposed by Zaheer et al. (NIPS 2017), we introduce a Set Aggregation Network (SAN) as an alternative…
Develops a binarized GNN for more efficient graph embeddings.
Combines PCA and message passing for better graph node embeddings.
Recent research on network embedding in hyperbolic space have proven successful in several applications. However, nodes in real world networks tend to interact through several distinct channels. Simple aggregation or ignorance of this multiplexity will lead to misleading results. On the other hand, there exists redunda…
CTGCN learns dynamic graph embeddings preserving both local and global graph structure.
Method reduces categorical data to lower dimensions using density matrices.