Search Results for author:
Found 43 papers, 26 papers with code
Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model
Recent advancements in computational chemistry have increasingly focused on synthesizing molecules based on textual instructions.
Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e. g., pruning inattentive tokens or merging similar tokens.
Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
Current solutions for efficiently constructing large vision-language (VL) models follow a two-step paradigm: projecting the output of pre-trained vision encoders to the input space of pre-trained language models as visual prompts; and then transferring the models to downstream VL tasks via end-to-end parameter-efficient fine-tuning (PEFT).
Empowering Large Language Model Agents through Action Learning
Large Language Model (LLM) Agents have recently garnered increasing interest yet they are limited in their ability to learn from trial and error, a key element of intelligent behavior.
Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy
Current state-of-the-art results in computer vision depend in part on fine-tuning large pre-trained vision models.
GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
We pretrain GIMLET on the molecule tasks along with instructions, enabling the model to transfer effectively to a broad range of tasks.
Dual-Alignment Pre-training for Cross-lingual Sentence Embedding
Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding.
Masked Image Modeling with Local Multi-Scale Reconstruction
The lower layers are not explicitly guided and the interaction among their patches is only used for calculating new activations.
Are More Layers Beneficial to Graph Transformers?
Despite that going deep has proven successful in many neural architectures, the existing graph transformers are relatively shallow.
Detachedly Learn a Classifier for Class-Incremental Learning
In continual learning, model needs to continually learn a feature extractor and classifier on a sequence of tasks.
FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer
Recent work has explored the potential to adapt a pre-trained vision transformer (ViT) by updating only a few parameters so as to improve storage efficiency, called parameter-efficient transfer learning (PETL).
Contrastive Prototypical Network with Wasserstein Confidence Penalty
This results in our CPN (Contrastive Prototypical Network) model, which combines the prototypical loss with pairwise contrast and outperforms the existing models from this paradigm with modestly large batch size.
Convolutional Bypasses Are Better Vision Transformer Adapters
The pretrain-then-finetune paradigm has been widely adopted in computer vision.
Certified Robustness Against Natural Language Attacks by Causal Intervention
Deep learning models have achieved great success in many fields, yet they are vulnerable to adversarial examples.
Bypassing Logits Bias in Online Class-Incremental Learning with a Generative Framework
In our framework, a generative classifier which utilizes replay memory is used for inference, and the training objective is a pair-based metric learning loss which is proven theoretically to optimize the feature space in a generative way.
Alleviating Representational Shift for Continual Fine-tuning
We study a practical setting of continual learning: fine-tuning on a pre-trained model continually.
Rethinking Minimal Sufficient Representation in Contrastive Learning
It significantly improves the performance of several classic contrastive learning models in downstream tasks.
G$^3$SR: Global Graph Guided Session-based Recommendation
G$^3$SR decomposes the session-based recommendation workflow into two steps.
Domain Adaptation via Maximizing Surrogate Mutual Information
In the framework, a surrogate joint distribution models the underlying joint distribution of the unlabeled target domain.
What Makes for Good Representations for Contrastive Learning
Therefore, we assume the task-relevant information that is not shared between views can not be ignored and theoretically prove that the minimal sufficient representation in contrastive learning is not sufficient for the downstream tasks, which causes performance degradation.
Cross-Domain Few-Shot Classification via Adversarial Task Augmentation
However, when there exists the domain shift between the training tasks and the test tasks, the obtained inductive bias fails to generalize across domains, which degrades the performance of the meta-learning models.
Ranked #2 on
Cross-Domain Few-Shot
on cars
BCFNet: A Balanced Collaborative Filtering Network with Attention Mechanism
Representation learning tries to learn a common low dimensional space for the representations of users and items.
Few-shot Learning with LSSVM Base Learner and Transductive Modules
The performance of meta-learning approaches for few-shot learning generally depends on three aspects: features suitable for comparison, the classifier ( base learner ) suitable for low-data scenarios, and valuable information from the samples to classify.
Self-Supervised Learning Aided Class-Incremental Lifelong Learning
Lifelong or continual learning remains to be a challenge for artificial neural network, as it is required to be both stable for preservation of old knowledge and plastic for acquisition of new knowledge.
Generative Feature Replay with Orthogonal Weight Modification for Continual Learning
For this scenario, generative replay is a promising strategy which generates and replays pseudo data for previous tasks to alleviate catastrophic forgetting.
Fast Structured Decoding for Sequence Models
However, these models assume that the decoding process of each token is conditionally independent of others.
Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning
We propose Dynamically Pruned Message Passing Networks (DPMPN) for large-scale knowledge graph reasoning.
Neural Consciousness Flow
Instead, inspired by the consciousness prior proposed by Yoshua Bengio, we explore reasoning with the notion of attentive awareness from a cognitive perspective, and formulate it in the form of attentive message passing on graphs, called neural consciousness flow (NeuCFlow).
Leap-LSTM: Enhancing Long Short-Term Memory for Text Categorization
Compared to previous models which can also skip words, our model achieves better trade-offs between performance and efficiency.
DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases
Furthermore, we propose a diversified point network to generate a set of diverse keyphrases out of the word graph in the decoding process.
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links.
Ranked #2 on
Link Prediction
on FB122
DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System
To solve this problem, many methods have been studied, which can be generally categorized into two types, i. e., representation learning-based CF methods and matching function learning-based CF methods.
Unsupervised Neural Word Segmentation for Chinese via Segmental Language Modeling
As far as we know, we are the first to propose a neural model for unsupervised CWS and achieve competitive performance to the state-of-the-art statistical models on four different datasets from SIGHAN 2005 bakeoff.
Learning to Compose over Tree Structures via POS Tags
Recursive Neural Network (RecNN), a type of models which compose words or phrases recursively over syntactic tree structures, has been proven to have superior ability to obtain sentence representation for a variety of NLP tasks.
MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation
Neural encoder-decoder models have been widely applied to conversational response generation, which is a research hot spot in recent years.
A Novel Framework for Recurrent Neural Networks with Enhancing Information Processing and Transmission between Units
This paper proposes a novel framework for recurrent neural networks (RNNs) inspired by the human memory models in the field of cognitive neuroscience to enhance information processing and transmission between adjacent RNNs' units.
A Gap-Based Framework for Chinese Word Segmentation via Very Deep Convolutional Networks
However, if we consider segmenting a given sentence, the most intuitive idea is to predict whether to segment for each gap between two consecutive characters, which in comparison makes previous approaches seem too complex.
Inter-Weighted Alignment Network for Sentence Pair Modeling
Sentence pair modeling is a crucial problem in the field of natural language processing.
An Unsupervised Multi-Document Summarization Framework Based on Neural Document Model
In the age of information exploding, multi-document summarization is attracting particular attention for the ability to help people get the main ideas in a short time.
