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.
New findings clarify the link between distributional closeness and representational similarity.
Deconfounds neural network representation similarity metrics to improve consistency and accuracy.
Develops an ordinal-similarity framework for scalable and interpretable representation alignment.
Recent work has sought to understand the behavior of neural networks by comparing representations between layers and between different trained models. We examine methods for comparing neural network representations based on canonical correlation analysis (CCA). We show that CCA belongs to a family of statistics for mea…
Unified understanding of neural representation similarity measures.
Logit distance bounds representational similarity of models.
Task loss matching misrepresents similarity between neural network layers.
Learning informative representations of data is one of the primary goals of deep learning, but there is still little understanding as to what representations a neural network actually learns. To better understand this, subspace match was recently proposed as a method for assessing the similarity of the representations …
This paper tackles noise in raw datasets to improve representation learning efficiency.
As a highlighting research topic in the multimedia area, cross-media retrieval aims to capture the complex correlations among multiple media types. Learning better shared representation and distance metric for multimedia data is important to boost the cross-media retrieval. Motivated by the strong ability of deep neura…
Geometric stability measures neural network robustness, distinguishing from similarity metrics.
Geospatial analysis lacks methods like the word vector representations and pre-trained networks that significantly boost performance across a wide range of natural language and computer vision tasks. To fill this gap, we introduce Tile2Vec, an unsupervised representation learning algorithm that extends the distribution…
New method certifies individual fairness in representations.
New method improves reinforcement learning generalization.
CLOCS uses contrastive learning to improve cardiac signal representations.
Centered Kernel Alignment (CKA) was recently proposed as a similarity metric for comparing activation patterns in deep networks. Here we experiment with the modified RV-coefficient (RV2), which has very similar properties as CKA while being less sensitive to dataset size. We compare the representations of networks that…
The paper tackles learning from similar but not identical linear representations, improving performance over single-task learning.
Paper proposes embedding models to capture semantic similarities of categorical attributes in financial bonds.
The paper explores how AI trading agents' similar information representation can cause financial market instability.
In this paper we study how different ways of combining character and word-level representations affect the quality of both final word and sentence representations. We provide strong empirical evidence that modeling characters improves the learned representations at the word and sentence levels, and that doing so is par…
We propose (WIPS) for neural network-based graph embedding. In addition to the parameters of neural networks, we optimize the weights of the inner product by allowing positive and negative values. Despite its simplicity, WIPS can approximate arbitrary general similarities in…
Self-supervised and supervised methods learn similar intermediate visual representations but diverge in final layers.
The study analyzes neural network predictions of knot invariants and finds that braid representations work best.
Introduces CHL, a new loss function for continuous similarity learning.
We propose a novel method of introducing structure into existing machine learning techniques by developing structure-based similarity and distance measures. To learn structural information, low-dimensional structure of the data is captured by solving a non-linear, low-rank representation problem. We show that this low-…
The paper analyzes MAML's representation using RSA, revealing that feature reuse is not the primary reason for its success.
New measures link neural representation geometry to decoding ability.
Defines a similarity measure for classification distributions.
A new method identifies similar mutual funds using graph learning.
It is a key to construct a similarity graph in graph-oriented subspace learning and clustering. In a similarity graph, each vertex denotes a data point and the edge weight represents the similarity between two points. There are two popular schemes to construct a similarity graph, i.e., pairwise distance based scheme an…
New framework to test neural network representation similarity measures.
MSA compares neural representations' intrinsic geometry for better understanding.
We consider the representation power of siamese-style similarity functions used in neural network-based graph embedding. The inner product similarity (IPS) with feature vectors computed via neural networks is commonly used for representing the strength of association between two nodes. However, only a little work has b…
Identifier names convey useful information about the intended semantics of code. Name-based program analyses use this information, e.g., to detect bugs, to predict types, and to improve the readability of code. At the core of name-based analyses are semantic representations of identifiers, e.g., in the form of learned …
Finding a new mathematical representations for graph, which allows direct comparison between different graph structures, is an open-ended research direction. Having such a representation is the first prerequisite for a variety of machine learning algorithms like classification, clustering, etc., over graph datasets. In…
The goal of unsupervised representation learning is to extract a new representation of data, such that solving many different tasks becomes easier. Existing methods typically focus on vectorized data and offer little support for relational data, which additionally describe relationships among instances. In this work we…
EMDE efficiently estimates manifold densities for diverse recommendation systems.
We train multi-task autoencoders on linguistic tasks and analyze the learned hidden sentence representations. The representations change significantly when translation and part-of-speech decoders are added. The more decoders a model employs, the better it clusters sentences according to their syntactic similarity, as t…
It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory and systematic approach quantitatively characterizing what representations do deep neural networks learn. In this work, we move a tiny step to…
GraphCL learns node representations by maximizing similarity between perturbed node features.
There are some similarities between cohomology of SU(2)-representation varieties of the fundamental group of some link complements and the Khovanov homology of the links. We start here a program to explain a possible source of these similarities. We introduce a symplectic manifold with an action of the b…
Proposes a new neural network approach to credit assignment.
Method measures weight similarity in neural networks using normalization and statistical inference.
Recent empirical works have successfully used unlabeled data to learn feature representations that are broadly useful in downstream classification tasks. Several of these methods are reminiscent of the well-known word2vec embedding algorithm: leveraging availability of pairs of semantically "similar" data points and "n…
Comparing different neural network representations and determining how representations evolve over time remain challenging open questions in our understanding of the function of neural networks. Comparing representations in neural networks is fundamentally difficult as the structure of representations varies greatly, e…
New findings on representation changes in transfer learning.
Real-valued word representations have transformed NLP applications; popular examples are word2vec and GloVe, recognized for their ability to capture linguistic regularities. In this paper, we demonstrate a {\em very simple}, and yet counter-intuitive, postprocessing technique -- eliminate the common mean vector and a f…
Paper shows similarity learning can lead to strong binary classification performance.