Search Results for author:
Found 22 papers, 15 papers with code
Improving Domain Adaptation through Extended-Text Reading Comprehension
To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method.
Combating Multi-path Interference to Improve Chirp-based Underwater Acoustic Communication
Linear chirp-based underwater acoustic communication has been widely used due to its reliability and long-range transmission capability.
Knowledge-based Multiple Adaptive Spaces Fusion for Recommendation
Specifically, in hyperbolic space, we set smaller margins in the area near to the origin, which is conducive to distinguishing between highly similar positive items and negative ones.
Adaptive Taxonomy Learning and Historical Patterns Modelling for Patent Classification
Finally, we combine the contextual information of patent texts that contains the semantics of IPC codes, and assignees' sequential preferences to make predictions.
Event-based Dynamic Graph Representation Learning for Patent Application Trend Prediction
Finally, the patent application trend is predicted by aggregating the representations of the target company and classification codes from static, dynamic, and hierarchical perspectives.
Scaling Sentence Embeddings with Large Language Models
We also fine-tune LLMs with current contrastive learning approach, and the 2. 7B OPT model, incorporating our prompt-based method, surpasses the performance of 4. 8B ST5, achieving the new state-of-the-art results on STS tasks.
Ranked #1 on
Semantic Textual Similarity
on STS12
Modeling Dynamic Heterogeneous Graph and Node Importance for Future Citation Prediction
To cope with this problem, we propose a Dynamic heterogeneous Graph and Node Importance network (DGNI) learning framework, which fully leverages the dynamic heterogeneous graph and node importance information to predict future citation trends of newly published papers.
Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph
However, existing HGNNs usually represent each node as a single vector in the multi-layer graph convolution calculation, which makes the high-level graph convolution layer fail to distinguish information from different relations and different orders, resulting in the information loss in the message passing.
A Survey on Causal Inference for Recommendation
Recently, causal inference has attracted increasing attention from researchers of recommender systems (RS), which analyzes the relationship between a cause and its effect and has a wide range of real-world applications in multiple fields.
RHCO: A Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning for Large-scale Graphs
To address these problems, we propose a novel Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning (RHCO) for large-scale heterogeneous graph representation learning.
Pruning Pre-trained Language Models Without Fine-Tuning
These methods, such as movement pruning, use first-order information to prune PLMs while fine-tuning the remaining weights.
Contrastive Learning with Bidirectional Transformers for Sequential Recommendation
Contrastive learning with Transformer-based sequence encoder has gained predominance for sequential recommendation.
Exploiting Global and Local Hierarchies for Hierarchical Text Classification
Existing methods encode label hierarchy in a global view, where label hierarchy is treated as the static hierarchical structure containing all labels.
Multi Label Text Classification
Multi-Label Text Classification
+1
Learnable Model Augmentation Self-Supervised Learning for Sequential Recommendation
To this end, in this paper, we propose a Learnable Model Augmentation self-supervised learning for sequential Recommendation (LMA4Rec).
PromptBERT: Improving BERT Sentence Embeddings with Prompts
We propose PromptBERT, a novel contrastive learning method for learning better sentence representation.
Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources
However, in the practical scenario, labeled data can be typically collected from multiple diverse sources, and they might be different not only from the target domain but also from each other.
Improving Non-autoregressive Generation with Mixup Training
While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge.
LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification
In LightXML, we use generative cooperative networks to recall and rank labels, in which label recalling part generates negative and positive labels, and label ranking part distinguishes positive labels from these labels.
Sparse Nonnegative CANDECOMP/PARAFAC Decomposition in Block Coordinate Descent Framework: A Comparison Study
In addition, we proposed an accelerated method to compute the objective function and relative error of sparse NCP, which has significantly improved the computation of tensor decomposition especially for higher-order tensor.
Cross-Domain Labeled LDA for Cross-Domain Text Classification
To this end, we embed the group alignment and a partial supervision into a cross-domain topic model, and propose a Cross-Domain Labeled LDA (CDL-LDA).
Feature Selection Based on Term Frequency and T-Test for Text Categorization
Much work has been done on feature selection.
Inverse-Category-Frequency based supervised term weighting scheme for text categorization
Term weighting schemes often dominate the performance of many classifiers, such as kNN, centroid-based classifier and SVMs.
Ranked #1 on
Multi-class Classification
on Reuters-52
