Search Results for author:
Found 62 papers, 27 papers with code
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
Moreover, our model even outperforms the largest closed LLMs, Anthropic's Claude and Google's Bard, on HumanEval and HumanEval+.
Ranked #3 on
Code Generation
on CodeContests
(Test Set pass@1 metric)
Rumor Detection on Twitter with Tree-structured Recursive Neural Networks
Automatic rumor detection is technically very challenging.
Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning
Massive false rumors emerging along with breaking news or trending topics severely hinder the truth.
A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection
Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances.
Fairness in Graph Mining: A Survey
Recently, algorithmic fairness has been extensively studied in graph-based applications.
Federated Graph Classification over Non-IID Graphs
Federated learning has emerged as an important paradigm for training machine learning models in different domains.
LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval
The conventional dense retrieval paradigm relies on encoding images and texts into dense representations using dual-stream encoders, however, it faces challenges with low retrieval speed in large-scale retrieval scenarios.
Augmented Large Language Models with Parametric Knowledge Guiding
We demonstrate that our PKG framework can enhance the performance of "black-box" LLMs on a range of domain knowledge-intensive tasks that require factual (+7. 9%), tabular (+11. 9%), medical (+3. 0%), and multimodal (+8. 1%) knowledge.
LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval
To address this issue, we propose a novel sparse retrieval paradigm for ITR that exploits sparse representations in the vocabulary space for images and texts.
Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning
The spread of rumors along with breaking events seriously hinders the truth in the era of social media.
Causal Inference in Recommender Systems: A Survey of Strategies for Bias Mitigation, Explanation, and Generalization
Traditional RSs estimate user interests and predict their future behaviors by utilizing correlations in the observational historical activities, their profiles, and the content of interacted items.
Learning Fair Node Representations with Graph Counterfactual Fairness
In this framework, we generate counterfactuals corresponding to perturbations on each node's and their neighbors' sensitive attributes.
Cross-lingual COVID-19 Fake News Detection
The COVID-19 pandemic poses a great threat to global public health.
Path-Specific Counterfactual Fairness for Recommender Systems
But since sensitive features may also affect user interests in a fair manner (e. g., race on culture-based preferences), indiscriminately eliminating all the influences of sensitive features inevitably degenerate the recommendations quality and necessary diversities.
Assessing the Causal Impact of COVID-19 Related Policies on Outbreak Dynamics: A Case Study in the US
Besides, as the confounders may be time-varying during COVID-19 (e. g., vigilance of residents changes in the course of the pandemic), it is even more difficult to capture them.
Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
Then we propose to fine-tune a small language model as the debate judge for harmfulness inference, to facilitate multimodal fusion between the harmfulness rationales and the intrinsic multimodal information within memes.
MMCode: Evaluating Multi-Modal Code Large Language Models with Visually Rich Programming Problems
Programming often involves converting detailed and complex specifications into code, a process during which developers typically utilize visual aids to more effectively convey concepts.
Learning from Crowds by Modeling Common Confusions
Crowdsourcing provides a practical way to obtain large amounts of labeled data at a low cost.
Ranked #1 on
Image Classification
on LabelMe
Coarse-To-Fine Incremental Few-Shot Learning
Such images form a new training set (i. e., support set) so that the incremental model is hoped to recognize a basenji (i. e., query) as a basenji next time.
Interpreting Unfairness in Graph Neural Networks via Training Node Attribution
In this paper, we study a novel problem of interpreting GNN unfairness through attributing it to the influence of training nodes.
Graph-based Alignment and Uniformity for Recommendation
To address this issue, we propose a novel approach, graph-based alignment and uniformity (GraphAU), that explicitly considers high-order connectivities in the user-item bipartite graph.
Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models
The age of social media is rife with memes.
Review-guided Helpful Answer Identification in E-commerce
In this paper, we propose the Review-guided Answer Helpfulness Prediction (RAHP) model that not only considers the interactions between QA pairs but also investigates the opinion coherence between the answer and crowds' opinions reflected in the reviews, which is another important factor to identify helpful answers.
WSDMS: Debunk Fake News via Weakly Supervised Detection of Misinforming Sentences with Contextualized Social Wisdom
This model only requires bag-level labels for training but is capable of inferring both sentence-level misinformation and article-level veracity, aided by relevant social media conversations that are attentively contextualized with news sentences.
DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy
The key idea is to decouple the feature projection and message passing via a DP PageRank algorithm which learns the structure information and uses the top-$K$ neighbors determined by the PageRank for feature aggregation.
NUAA-QMUL at SemEval-2020 Task 8: Utilizing BERT and DenseNet for Internet Meme Emotion Analysis
This paper describes our contribution to SemEval 2020 Task 8: Memotion Analysis.
Detect Rumors in Microblog Posts Using Propagation Structure via Kernel Learning
How fake news goes viral via social media?
EICA Team at SemEval-2017 Task 3: Semantic and Metadata-based Features for Community Question Answering
In the main Subtask C, our primary submission was ranked fourth, with a MAP of 13. 48 and accuracy of 97. 08.
Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks
Claim verification is generally a task of verifying the veracity of a given claim, which is critical to many downstream applications.
Privacy-Preserving Tensor Factorization for Collaborative Health Data Analysis
We propose DPFact, a privacy-preserving collaborative tensor factorization method for computational phenotyping using EHR.
Spatio-Temporal Tensor Sketching via Adaptive Sampling
In this paper, we propose SkeTenSmooth, a novel tensor factorization framework that uses adaptive sampling to compress the tensor in a temporally streaming fashion and preserves the underlying global structure.
AnswerFact: Fact Checking in Product Question Answering
Product-related question answering platforms nowadays are widely employed in many E-commerce sites, providing a convenient way for potential customers to address their concerns during online shopping.
Transferable Multi-level Attention Neural Network for Accurate Prediction of Quantum Chemistry Properties via Multi-task Learning
The development of efficient models for predicting specific properties through machine learning is of great importance for the innovation of chemistry and material science.
Ranked #7 on
Formation Energy
on QM9
Analysis and classification of main risk factors causing stroke in Shanxi Province
Evaluation of the risk of getting stroke is important for the prevention and treatment of stroke in China.
Multi-objective optimization and explanation for stroke risk assessment in Shanxi province
The experimental results showed that the QIDNN model with 7 interactive features achieve the state-of-art accuracy $83. 25\%$.
Temporal Network Embedding via Tensor Factorization
Representation learning on static graph-structured data has shown a significant impact on many real-world applications.
Communication Efficient Generalized Tensor Factorization for Decentralized Healthcare Networks
Tensor factorization has been proved as an efficient unsupervised learning approach for health data analysis, especially for computational phenotyping, where the high-dimensional Electronic Health Records (EHRs) with patients' history of medical procedures, medications, diagnosis, lab tests, etc., are converted to meaningful and interpretable medical concepts.
Debunking Rumors on Twitter with Tree Transformer
Rumors are manufactured with no respect for accuracy, but can circulate quickly and widely by {``}word-of-post{''} through social media conversations.
Analyzing the Implicit Position Encoding Ability of Transformer Decoder
A common limitation of Transformer Encoder's self-attention mechanism is that it cannot automatically capture the information of word order, so one needs to feed the explicit position encodings into the target model.
Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks
Rumors are rampant in the era of social media.
Malicious Mode Attack on EV Coordinated Charging Load and MIADRC Defense Strategy
Further, to mitigate the impact of MMA, a defense strategy based on multi-index information active disturbance rejection control is proposed to improve the stability and anti-disturbance ability of the power system, which considers the impact factors of both mode damping and disturbance compensation.
HiTRANS: A Hierarchical Transformer Network for Nested Named Entity Recognition
Specifically, we first utilize a two-phase module to generate span representations by aggregating context information based on a bottom-up and top-down transformer network.
A Frustratingly Simple Approach for End-to-End Image Captioning
Before training the captioning models, an extra object detector is utilized to recognize the objects in the image at first.
I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning
Different to these heavy-cost models, we introduce a lightweight image captioning framework (I-Tuning), which contains a small number of trainable parameters.
A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning
The diffusion of rumors on microblogs generally follows a propagation tree structure, that provides valuable clues on how an original message is transmitted and responded by users over time.
DecBERT: Enhancing the Language Understanding of BERT with Causal Attention Masks
In contrast, Transformer Decoder with the causal attention masks is naturally sensitive to the word order.
Empowering Next POI Recommendation with Multi-Relational Modeling
Noticeably, LBSNs have offered unparalleled access to abundant heterogeneous relational information about users and POIs (including user-user social relations, such as families or colleagues; and user-POI visiting relations).
Aligning Logits Generatively for Principled Black-Box Knowledge Distillation
Black-Box Knowledge Distillation (B2KD) is a formulated problem for cloud-to-edge model compression with invisible data and models hosted on the server.
Learning Causal Effects on Hypergraphs
Hypergraphs provide an effective abstraction for modeling multi-way group interactions among nodes, where each hyperedge can connect any number of nodes.
CLEAR: Generative Counterfactual Explanations on Graphs
Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?".
Private Semi-supervised Knowledge Transfer for Deep Learning from Noisy Labels
PATE combines an ensemble of "teacher models" trained on sensitive data and transfers the knowledge to a "student" model through the noisy aggregation of teachers' votes for labeling unlabeled public data which the student model will be trained on.
NUAA-QMUL-AIIT at Memotion 3: Multi-modal Fusion with Squeeze-and-Excitation for Internet Meme Emotion Analysis
This paper describes the participation of our NUAA-QMUL-AIIT team in the Memotion 3 shared task on meme emotion analysis.
Cluster-based Deep Ensemble Learning for Emotion Classification in Internet Memes
Memes have gained popularity as a means to share visual ideas through the Internet and social media by mixing text, images and videos, often for humorous purposes.
A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detection
The truth is significantly hampered by massive rumors that spread along with breaking news or popular topics.
A Look into Causal Effects under Entangled Treatment in Graphs: Investigating the Impact of Contact on MRSA Infection
In this paper, we study the problem of causal effect estimation with treatment entangled in a graph.
Learning for Counterfactual Fairness from Observational Data
A prerequisite for existing methods to achieve counterfactual fairness is the prior human knowledge of the causal model for the data.
Fair Few-shot Learning with Auxiliary Sets
These auxiliary sets contain several labeled training samples that can enhance the model performance regarding fairness in meta-test tasks, thereby allowing for the transfer of learned useful fairness-oriented knowledge to meta-test tasks.
GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse
The exponential growth of social media has profoundly transformed how information is created, disseminated, and absorbed, exceeding any precedent in the digital age.
Efficient LLM inference solution on Intel GPU
A customized Scaled-Dot-Product-Attention kernel is designed to match our fusion policy based on the segment KV cache solution.
Cyclic Neural Network
This paper answers a fundamental question in artificial neural network (ANN) design: We do not need to build ANNs layer-by-layer sequentially to guarantee the Directed Acyclic Graph (DAG) property.
AI WALKUP: A Computer-Vision Approach to Quantifying MDS-UPDRS in Parkinson's Disease
Parkinson's Disease (PD) is the second most common neurodegenerative disorder.
