Graph Neural Networks (GNNs) have been widely applied to fraud detection problems in recent years, revealing the suspiciousness of nodes by aggregating their neighborhood information via different relations However, few prior works have noticed the camouflage behavior of fraudsters, which could hamper the performance of GNN-based fraud detectors during the aggregation process In this paper, we introduce two types of camouflages based on recent empirical studies, ie, the feature camouflage and the relation camouflage Existing GNNs have not addressed these two camouflages, which results in their poor performance in fraud detection problems Alternatively, we propose a new model named CAmouflage-REsistant GNN (CARE-GNN), to enhance the GNN aggregation process with three unique modules against camouflages Concretely, we first devise a label-aware similarity measure to find informative neighboring nodes Then, we leverage reinforcement learning (RL) to find the optimal amounts of neighbors to be selected Finally, the selected neighbors across different relations are aggregated together Comprehensive experiments on two real-world fraud datasets demonstrate the effectiveness of the RL algorithm The proposed CARE-GNN also outperforms state-of-the-art GNNs and GNN-based fraud detectors We integrate all GNN-based fraud detectors as an opensource toolbox: this https URL The CARE-GNN code and datasets are available at this https URL

Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

International Quarterly of Community Health Education

Graph Neural Networks (GNNs) have been widely applied to fraud detection problems in recent years, revealing the suspiciousness of nodes by aggregating their neighborhood information via different relations. However, few prior works have noticed the camouflage behavior of fraudsters, which could hamper the performance of GNN-based fraud detectors during the aggregation process. In this paper, we introduce two types of camouflages based on recent empirical studies, i.e., the feature camouflage and the relation camouflage. Existing GNNs have not addressed these two camouflages, which results in their poor performance in fraud detection problems. Alternatively, we propose a new model named CAmouflage-REsistant GNN (CARE-GNN), to enhance the GNN aggregation process with three unique modules against camouflages. Concretely, we first devise a label-aware similarity measure to find informative neighboring nodes. Then, we leverage reinforcement learning (RL) to find the optimal amounts of neighbors to be selected. Finally, the selected neighbors across different relations are aggregated together. Comprehensive experiments on two real-world fraud datasets demonstrate the effectiveness of the RL algorithm. The proposed CARE-GNN also outperforms state-of-the-art GNNs and GNN-based fraud detectors. We integrate all GNN-based fraud detectors as an opensource toolbox https://github.com/safe-graph/DGFraud. The CARE-GNN code and datasets are available at https://github.com/YingtongDou/CARE-GNN.

https://dl.acm.org/doi/pdf/10.1145/3340531.3411903

This paper explores a simple method for improving the zero-shot learning abilities of language models. We show that instruction tuning -- finetuning language models on a collection of tasks described via instructions -- substantially boosts zero-shot performance on unseen tasks. 
We take a 137B parameter pretrained language model and instruction-tune it on over 60 NLP tasks verbalized via natural language instruction templates. We evaluate this instruction-tuned model, which we call FLAN, on unseen task types. FLAN substantially improves the performance of its unmodified counterpart and surpasses zero-shot 175B GPT-3 on 19 of 25 tasks that we evaluate. FLAN even outperforms few-shot GPT-3 by a large margin on ANLI, RTE, BoolQ, AI2-ARC, OpenbookQA, and StoryCloze. Ablation studies reveal that number of tasks and model scale are key components to the success of instruction tuning.

Finetuned Language Models Are Zero-Shot Learners

Although large language models (LLMs) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, we introduce the concept of Chaining LLM steps together, where the output of one step becomes the input for the next, thus aggregating the gains per step. We first define a set of LLM primitive operations useful for Chain construction, then present an interactive system where users can modify these Chains, along with their intermediate results, in a modular way. In a 20-person user study, we found that Chaining not only improved the quality of task outcomes, but also significantly enhanced system transparency, controllability, and sense of collaboration. Additionally, we saw that users developed new ways of interacting with LLMs through Chains: they leveraged sub-tasks to calibrate model expectations, compared and contrasted alternative strategies by observing parallel downstream effects, and debugged unexpected model outputs by "unit-testing" sub-components of a Chain. In two case studies, we further explore how LLM Chains may be used in future applications.

AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts

Modern social media relies on high quality user generated writing such as reviews, explanations, and answers. In contrast to standard validation to provide feedback for structured inputs (e.g., dates, email addresses), it is difficult to provide timely, high quality, customized feedback for free-form text input. While existing solutions based on crowdsourced feedback (e.g., up-votes and comments) can eventually produce high quality feedback, they suffer from high latency and costs, whereas fully automated approaches are limited to syntactic feedback that does not address text content. We introduce Dialectic, an end-to-end extensible system that simplifies the process of creating, customizing, and deploying content-specific feedback for free-text inputs. Our main observation is that many services already have a corpus of crowdsourced feedback that can be used to bootstrap a feedback system. Dialectic initializes with a corpus of annotated free-form text, automatically segments input text, and helps developers rapidly add domain-specific document quality features as well as content-specific feedback generation functions to provide targeted feedback to user inputs. Our user study shows that Dialectic can be used to create a feedback interface that produces an average of 14.4\% quality improvement of product review text, over 3x better than a state-of-the-art feedback system.

Dialectic: Enhancing Text Input Fields with Automatic Feedback to Improve Social Content Writing Quality.

An automated medical procedure order recommender can facilitate patient referrals and consultations from primary care providers to specialty care sites. Here, we propose to solve this task using a novel graph representation learning approach. We develop a heterogeneous graph neural network to model structured electronic health records and formulate the procedure recommender task as a link prediction problem. Our experimental results show that our model achieves a 14% improvement in personalized recommendations over state-of-the-art neural network models and existing clinical tools including referral guidelines and check lists.

https://www.medrxiv.org/content/medrxiv/early/2023/04/04/2022.11.21.22282571.full.pdf

Graph-Based Clinical Recommender: Predicting Specialists Procedure Orders using Graph Representation Learning

Predicting how different interventions will causally affect a specific individual is important in a variety of domains such as personalized medicine, public policy, and online marketing. There are a large number of methods to predict the effect of an existing intervention based on historical data from individuals who received it. However, in many settings it is important to predict the effects of novel interventions (\emph{e.g.}, a newly invented drug), which these methods do not address. Here, we consider zero-shot causal learning: predicting the personalized effects of a novel intervention. We propose CaML, a causal meta-learning framework which formulates the personalized prediction of each intervention's effect as a task. CaML trains a single meta-model across thousands of tasks, each constructed by sampling an intervention, along with its recipients and nonrecipients. By leveraging both intervention information (\emph{e.g.}, a drug's attributes) and individual features~(\emph{e.g.}, a patient's history), CaML is able to predict the personalized effects of novel interventions that do not exist at the time of training. Experimental results on real world datasets in large-scale medical claims and cell-line perturbations demonstrate the effectiveness of our approach. Most strikingly, CaML's zero-shot predictions outperform even strong baselines trained directly on data from the test interventions.

Hamed Nilforoshan

Papers

Dialectic: Enhancing Text Input Fields with Automatic Feedback to Improve Social Content Writing Quality.

Graph-Based Clinical Recommender: Predicting Specialists Procedure Orders using Graph Representation Learning

Zero-shot causal learning