Search Results for author:
Found 42 papers, 12 papers with code
Can a Large Language Model Learn Matrix Functions In Context?
Large Language Models (LLMs) have demonstrated the ability to solve complex tasks through In-Context Learning (ICL), where models learn from a few input-output pairs without explicit fine-tuning.
Automating Data Science Pipelines with Tensor Completion
Hyperparameter optimization is an essential component in many data science pipelines and typically entails exhaustive time and resource-consuming computations in order to explore the combinatorial search space.
Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive Training
This can become problematic for all sampling methods, especially when we move to parallel sampling which requires us to initialize and update the entire sample trajectory of dynamics in parallel, leading to many OOD evaluations.
TRAWL: Tensor Reduced and Approximated Weights for Large Language Models
Recent research has shown that pruning large-scale language models for inference is an effective approach to improving model efficiency, significantly reducing model weights with minimal impact on performance.
GPT-generated Text Detection: Benchmark Dataset and Tensor-based Detection Method
As natural language models like ChatGPT become increasingly prevalent in applications and services, the need for robust and accurate methods to detect their output is of paramount importance.
Towards Aligned Canonical Correlation Analysis: Preliminary Formulation and Proof-of-Concept Results
Canonical Correlation Analysis (CCA) has been widely applied to jointly embed multiple views of data in a maximally correlated latent space.
CARL-G: Clustering-Accelerated Representation Learning on Graphs
CARL-G is adaptable to different clustering methods and CVIs, and we show that with the right choice of clustering method and CVI, CARL-G outperforms node classification baselines on 4/5 datasets with up to a 79x training speedup compared to the best-performing baseline.
Link Prediction with Non-Contrastive Learning
In this work, we extensively evaluate the performance of existing non-contrastive methods for link prediction in both transductive and inductive settings.
FRAPPE: $\underline{\text{F}}$ast $\underline{\text{Ra}}$nk $\underline{\text{App}}$roximation with $\underline{\text{E}}$xplainable Features for Tensors
We can then train a specialized single-use regression model on a synthetic set of tensors engineered to match a given input tensor and use that to estimate the canonical rank of the tensor - all without computing the expensive CPD.
MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning
The first algorithm, IVIPER, extends VIPER, a recent method for single-agent interpretable RL, to the multi-agent setting.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Deepfake Representation with Multilinear Regression
Generative neural network architectures such as GANs, may be used to generate synthetic instances to compensate for the lack of real data.
Subspace Clustering Based Analysis of Neural Networks
These experiments reveal that as we go deeper in a network, inputs tend to have an increasing affinity to other inputs of the same class.
KNH: Multi-View Modeling with K-Nearest Hyperplanes Graph for Misinformation Detection
In this work, we introduce a novel generalization of graphs i. e., K-Nearest Hyperplanes graph (KNH) where the nodes are defined by higher order Euclidean subspaces for multi-view modeling of the nodes.
Identifying Misinformation from Website Screenshots
To capture this overall look, we take screenshots of news articles served by either misinformative or trustworthy web domains and leverage a tensor decomposition based semi-supervised classification technique.
Analyzing Representations inside Convolutional Neural Networks
In this work, we propose a framework to categorize the concepts a network learns based on the way it clusters a set of input examples, clusters neurons based on the examples they activate for, and input features all in the same latent space.
RecTen: A Recursive Hierarchical Low Rank Tensor Factorization Method to Discover Hierarchical Patterns in Multi-modal Data
How can we expand the tensor decomposition to reveal a hierarchical structure of the multi-modal data in a self-adaptive way?
TenFor: A Tensor-Based Tool to Extract Interesting Events from Security Forums
Our approach and our platform constitute an important step towards detecting activities of interest from a forum in an unsupervised learning fashion in practice.
Ensemble Node Embeddings using Tensor Decomposition: A Case-Study on DeepWalk
Node embeddings have been attracting increasing attention during the past years.
Semi-Supervised Multi-aspect Detection of Misinformation using Hierarchical Joint Decomposition
Distinguishing between misinformation and real information is one of the most challenging problems in today's interconnected world.
TensorShield: Tensor-based Defense Against Adversarial Attacks on Images
Subtle and imperceptible perturbations of the data are able to change the result of deep neural networks.
REST: A Thread Embedding Approach for Identifying and Classifying User-specified Information in Security Forums
How can we extract useful information from a security forum?
Adaptive Granularity in Tensors: A Quest for Interpretable Structure
Data collected at very frequent intervals is usually extremely sparse and has no structure that is exploitable by modern tensor decomposition algorithms.
The core consistency of a compressed tensor
Among the most popular methods is a class of algorithms that leverages compression in order to reduce the size of the tensor and potentially parallelize computations.
Representation Learning by Reconstructing Neighborhoods
Since its introduction, unsupervised representation learning has attracted a lot of attention from the research community, as it is demonstrated to be highly effective and easy-to-apply in tasks such as dimension reduction, clustering, visualization, information retrieval, and semi-supervised learning.
Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval
Inspired by the recent success of webly supervised learning in deep neural networks, we capitalize on readily-available web images with noisy annotations to learn robust image-text joint representation.
OCTen: Online Compression-based Tensor Decomposition
Tensor decompositions are powerful tools for large data analytics as they jointly model multiple aspects of data into one framework and enable the discovery of the latent structures and higher-order correlations within the data.
A Constrained Coupled Matrix-Tensor Factorization for Learning Time-evolving and Emerging Topics
In this paper, we propose a novel time-evolving topic discovery method which, in addition to the extracted topics, is able to identify the evolution of that topic over time, as well as the level of difficulty of that topic, as it is inferred by the level of expertise of its main contributors.
A Peek Into the Hidden Layers of a Convolutional Neural Network Through a Factorization Lens
Furthermore, can we characterize a given deep neural network based on it's observed behavior on different inputs?
RECS: Robust Graph Embedding Using Connection Subgraphs
Representation learning algorithms aim to preserve local and global network structure by identifying node neighborhood notions.
t-PINE: Tensor-based Predictable and Interpretable Node Embeddings
Contrary to baseline methods, which generally learn explicit graph representations by solely using an adjacency matrix, t-PINE avails a multi-view information graph, the adjacency matrix represents the first view, and a nearest neighbor adjacency, computed over the node features, is the second view, in order to learn explicit and implicit node representations, using the Canonical Polyadic (a. k. a.
Identifying and Alleviating Concept Drift in Streaming Tensor Decomposition
In this paper, we define "concept" and "concept drift" in the context of streaming tensor decomposition, as the manifestation of the variability of latent concepts throughout the stream.
Semi-supervised Content-based Detection of Misinformation via Tensor Embeddings
Most existing works on this topic focus on manual feature extraction and supervised classification models leveraging a large number of labeled (fake or real) articles.
RIPEx: Extracting malicious IP addresses from security forums using cross-forum learning
We propose RIPEx, a systematic approach to identify and label IP addresses in security forums by utilizing a cross-forum learning method.
SUSTain: Scalable Unsupervised Scoring for Tensors and its Application to Phenotyping
We propose two variants, SUSTain_M and SUSTain_T, to handle both matrix and tensor inputs, respectively.
COPA: Constrained PARAFAC2 for Sparse & Large Datasets
To tackle these challenges, we propose a {\it CO}nstrained {\it PA}RAFAC2 (COPA) method, which carefully incorporates optimization constraints such as temporal smoothness, sparsity, and non-negativity in the resulting factors.
Neighbor-encoder
By reformulating the representation learning problem as a neighbor reconstruction problem, domain knowledge can be easily incorporated with appropriate definition of similarity or distance between objects.
The Exact Solution to Rank-1 L1-norm TUCKER2 Decomposition
We study rank-1 {L1-norm-based TUCKER2} (L1-TUCKER2) decomposition of 3-way tensors, treated as a collection of $N$ $D \times M$ matrices that are to be jointly decomposed.
Balancing Interpretability and Predictive Accuracy for Unsupervised Tensor Mining
Previously, we have proposed an automated tensor mining method which leverages a well-known quality heuristic from the field of Chemometrics, the Core Consistency Diagnostic (CORCONDIA), in order to automatically determine the rank for the PARAFAC decomposition.
SamBaTen: Sampling-based Batch Incremental Tensor Decomposition
In this paper we introduce SaMbaTen, a Sampling-based Batch Incremental Tensor Decomposition algorithm, which incrementally maintains the decomposition given new updates to the tensor dataset.
SPARTan: Scalable PARAFAC2 for Large & Sparse Data
For example, when modeling medical features across a set of patients, the number and duration of treatments may vary widely in time, meaning there is no meaningful way to align their clinical records across time points for analysis purposes.
Tensor Decomposition for Signal Processing and Machine Learning
Tensors or {\em multi-way arrays} are functions of three or more indices $(i, j, k,\cdots)$ -- similar to matrices (two-way arrays), which are functions of two indices $(r, c)$ for (row, column).
Automatic Unsupervised Tensor Mining with Quality Assessment
A popular tool for unsupervised modelling and mining multi-aspect data is tensor decomposition.
