Search Results for author:
Found 28 papers, 10 papers with code
A Comprehensive Survey of Compression Algorithms for Language Models
How can we compress language models without sacrificing accuracy?
Cold-start Bundle Recommendation via Popularity-based Coalescence and Curriculum Heating
To estimate the user-bundle relationship more accurately, CoHeat addresses the highly skewed distribution of bundle interactions through a popularity-based coalescence approach, which incorporates historical and affiliation information based on the bundle's popularity.
Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance
It is important to have a general method for measuring transferability that can be applied in a variety of situations, such as selecting the best self-supervised pre-trained models that do not have classifiers, and selecting the best transferring layer for a target task.
Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models
As a result, K-prune shows significant accuracy improvements up to 58. 02%p higher F1 score compared to existing retraining-free pruning algorithms under a high compression rate of 80% on the SQuAD benchmark without any retraining process.
Fast and Accurate Dual-Way Streaming PARAFAC2 for Irregular Tensors -- Algorithm and Application
Although real-time analysis is necessary in the dual-way streaming, static PARAFAC2 decomposition methods fail to efficiently work in this setting since they perform PARAFAC2 decomposition for accumulated tensors whenever new data arrive.
Accurate Open-set Recognition for Memory Workload
How can we accurately identify new memory workloads while classifying known memory workloads?
Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters
BundleMage effectively mixes user preferences of items and bundles using an adaptive gate technique to achieve high accuracy for the bundle matching.
Diversely Regularized Matrix Factorization for Accurate and Aggregately Diversified Recommendation
However, it is challenging to tackle aggregate-level diversity with a matrix factorization (MF), one of the most common recommendation model, since skewed real world data lead to skewed recommendation results of MF.
Accurate Action Recommendation for Smart Home via Two-Level Encoders and Commonsense Knowledge
SmartSense then summarizes sequences of users considering queried contexts in a query-attentive manner to extract the query-related patterns from the sequential actions.
Accurate Node Feature Estimation with Structured Variational Graph Autoencoder
Given a graph with partial observations of node features, how can we estimate the missing features accurately?
DPar2: Fast and Scalable PARAFAC2 Decomposition for Irregular Dense Tensors
In this paper, we propose DPar2, a fast and scalable PARAFAC2 decomposition method for irregular dense tensors.
Model-Agnostic Augmentation for Accurate Graph Classification
Then, we propose NodeSam (Node Split and Merge) and SubMix (Subgraph Mix), two model-agnostic approaches for graph augmentation that satisfy all desired properties with different motivations.
Multi-EPL: Accurate Multi-source Domain Adaptation
Given multiple source datasets with labels, how can we train a target model with no labeled data?
Signed Graph Diffusion Network
In this paper, we propose Signed Graph Diffusion Network (SGDNet), a novel graph neural network that achieves end-to-end node representation learning for link sign prediction in signed social graphs.
T-GAP: Learning to Walk across Time for Temporal Knowledge Graph Completion
However, most of the existing mod-els for TKG completion extend static KG embeddings that donot fully exploit TKG structure, thus lacking in 1) account-ing for temporally relevant events already residing in the lo-cal neighborhood of a query, and 2) path-based inference that facilitates multi-hop reasoning and better interpretability.
Time-Aware Tensor Decomposition for Missing Entry Prediction
The essential problems of how to exploit the temporal property for tensor decomposition and consider the sparsity of time slices remain unresolved.
Pea-KD: Parameter-efficient and Accurate Knowledge Distillation on BERT
PTP is a KD-specialized initialization method, which can act as a good initial guide for the student.
Ensemble Multi-Source Domain Adaptation with Pseudolabels
Multi-source domain adaptation (MSDA) aims to train a model using multiple source datasets different from a target dataset in the absence of target data labels.
Pea-KD: Parameter-efficient and accurate Knowledge Distillation
SPS is a new parameter sharing method that allows greater model complexity for the student model.
Fast Partial Fourier Transform
In this paper, we propose a fast Partial Fourier Transform (PFT), a careful modification of the Cooley-Tukey algorithm that enables one to specify an arbitrary consecutive range where the coefficients should be computed.
Fast and Accurate Transferability Measurement for Heterogeneous Multivariate Data
We address the problem of measuring transferability between source and target datasets, where the source and the target have different feature spaces and distributions.
Knowledge Extraction with No Observable Data
Knowledge distillation is to transfer the knowledge of a large neural network into a smaller one and has been shown to be effective especially when the amount of training data is limited or the size of the student model is very small.
FALCON: Lightweight and Accurate Convolution
By exploiting the knowledge of a trained standard model and carefully determining the order of depthwise separable convolution via GEP, FALCON achieves sufficient accuracy close to that of the trained standard model.
FALCON: Fast and Lightweight Convolution for Compressing and Accelerating CNN
A promising direction is based on depthwise separable convolution which replaces a standard convolution with a depthwise convolution and a pointwise convolution.
Transfer Alignment Network for Double Blind Unsupervised Domain Adaptation
In this paper, we define the problem of unsupervised domain adaptation under double blind constraint, where either the source or the target domain cannot observe the data in the other domain, but data from both domains are used for training.
Data Context Adaptation for Accurate Recommendation with Additional Information
Given a sparse rating matrix and an auxiliary matrix of users or items, how can we accurately predict missing ratings considering different data contexts of entities?
Efficient Learning of Bounded-Treewidth Bayesian Networks from Complete and Incomplete Data Sets
We present a novel anytime algorithm (k-MAX) method for this task, which scales up to thousands of variables.
