Alert button
Picture for Zhen Zhang

Zhen Zhang

Alert button

Identifiable Latent Polynomial Causal Models Through the Lens of Change

Oct 24, 2023
Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton van den Hengel, Kun Zhang, Javen Qinfeng Shi

Figure 1 for Identifiable Latent Polynomial Causal Models Through the Lens of Change
Figure 2 for Identifiable Latent Polynomial Causal Models Through the Lens of Change
Figure 3 for Identifiable Latent Polynomial Causal Models Through the Lens of Change
Figure 4 for Identifiable Latent Polynomial Causal Models Through the Lens of Change

Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as identifiability. A recent breakthrough explores identifiability by leveraging the change of causal influences among latent causal variables across multiple environments \citep{liu2022identifying}. However, this progress rests on the assumption that the causal relationships among latent causal variables adhere strictly to linear Gaussian models. In this paper, we extend the scope of latent causal models to involve nonlinear causal relationships, represented by polynomial models, and general noise distributions conforming to the exponential family. Additionally, we investigate the necessity of imposing changes on all causal parameters and present partial identifiability results when part of them remains unchanged. Further, we propose a novel empirical estimation method, grounded in our theoretical finding, that enables learning consistent latent causal representations. Our experimental results, obtained from both synthetic and real-world data, validate our theoretical contributions concerning identifiability and consistency.

Viaarxiv icon

Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFT

Oct 19, 2023
Zhen Zhang, Bingqiao Luo, Shengliang Lu, Bingsheng He

Numerous studies have been conducted to investigate the properties of large-scale temporal graphs. Despite the ubiquity of these graphs in real-world scenarios, it's usually impractical for us to obtain the whole real-time graphs due to privacy concerns and technical limitations. In this paper, we introduce the concept of {\it Live Graph Lab} for temporal graphs, which enables open, dynamic and real transaction graphs from blockchains. Among them, Non-fungible tokens (NFTs) have become one of the most prominent parts of blockchain over the past several years. With more than \$40 billion market capitalization, this decentralized ecosystem produces massive, anonymous and real transaction activities, which naturally forms a complicated transaction network. However, there is limited understanding about the characteristics of this emerging NFT ecosystem from a temporal graph analysis perspective. To mitigate this gap, we instantiate a live graph with NFT transaction network and investigate its dynamics to provide new observations and insights. Specifically, through downloading and parsing the NFT transaction activities, we obtain a temporal graph with more than 4.5 million nodes and 124 million edges. Then, a series of measurements are presented to understand the properties of the NFT ecosystem. Through comparisons with social, citation, and web networks, our analyses give intriguing findings and point out potential directions for future exploration. Finally, we also study machine learning models in this live graph to enrich the current datasets and provide new opportunities for the graph community. The source codes and dataset are available at https://livegraphlab.github.io.

* Accepted by NeurIPS 2023, Datasets and Benchmarks Track 
Viaarxiv icon

ETGraph: A Pioneering Dataset Bridging Ethereum and Twitter

Oct 17, 2023
Qian Wang, Zhen Zhang, Zemin Liu, Shengliang Lu, Bingqiao Luo, Bingsheng He

While numerous public blockchain datasets are available, their utility is constrained by a singular focus on blockchain data. This constraint limits the incorporation of relevant social network data into blockchain analysis, thereby diminishing the breadth and depth of insight that can be derived. To address the above limitation, we introduce ETGraph, a novel dataset that authentically links Ethereum and Twitter, marking the first and largest dataset of its kind. ETGraph combines Ethereum transaction records (2 million nodes and 30 million edges) and Twitter following data (1 million nodes and 3 million edges), bonding 30,667 Ethereum addresses with verified Twitter accounts sourced from OpenSea. Detailed statistical analysis on ETGraph highlights the structural differences between Twitter-matched and non-Twitter-matched Ethereum addresses. Extensive experiments, including Ethereum link prediction, wash-trading Ethereum addresses detection, and Twitter-Ethereum matching link prediction, emphasize the significant role of Twitter data in enhancing Ethereum analysis. ETGraph is available at https://etgraph.deno.dev/.

Viaarxiv icon

Interactive Navigation in Environments with Traversable Obstacles Using Large Language and Vision-Language Models

Oct 13, 2023
Zhen Zhang, Anran Lin, Chun Wai Wong, Xiangyu Chu, Qi Dou, K. W. Samuel Au

This paper proposes an interactive navigation framework by using large language and vision-language models, allowing robots to navigate in environments with traversable obstacles. We utilize the large language model (GPT-3.5) and the open-set Vision-language Model (Grounding DINO) to create an action-aware costmap to perform effective path planning without fine-tuning. With the large models, we can achieve an end-to-end system from textual instructions like "Can you pass through the curtains to deliver medicines to me?", to bounding boxes (e.g., curtains) with action-aware attributes. They can be used to segment LiDAR point clouds into two parts: traversable and untraversable parts, and then an action-aware costmap is constructed for generating a feasible path. The pre-trained large models have great generalization ability and do not require additional annotated data for training, allowing fast deployment in the interactive navigation tasks. We choose to use multiple traversable objects such as curtains and grasses for verification by instructing the robot to traverse them. Besides, traversing curtains in a medical scenario was tested. All experimental results demonstrated the proposed framework's effectiveness and adaptability to diverse environments.

* 7 pages, 8 figures 
Viaarxiv icon

RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue

Sep 18, 2023
Zhengliang Shi, Weiwei Sun, Shuo Zhang, Zhen Zhang, Pengjie Ren, Zhaochun Ren

Figure 1 for RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue
Figure 2 for RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue
Figure 3 for RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue
Figure 4 for RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue

Evaluating open-domain dialogue systems is challenging for reasons such as the one-to-many problem, i.e., many appropriate responses other than just the golden response. As of now, automatic evaluation methods need better consistency with humans, while reliable human evaluation can be time- and cost-intensive. To this end, we propose the Reference-Assisted Dialogue Evaluation (RADE) approach under the multi-task learning framework, which leverages the pre-created utterance as reference other than the gold response to relief the one-to-many problem. Specifically, RADE explicitly compares reference and the candidate response to predict their overall scores. Moreover, an auxiliary response generation task enhances prediction via a shared encoder. To support RADE, we extend three datasets with additional rated responses other than just a golden response by human annotation. Experiments on our three datasets and two existing benchmarks demonstrate the effectiveness of our method, where Pearson, Spearman, and Kendall correlations with human evaluation outperform state-of-the-art baselines.

* 19 pages, Accepted by ACL2023 main conference 
Viaarxiv icon

Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates

Sep 15, 2023
Insu Jang, Zhenning Yang, Zhen Zhang, Xin Jin, Mosharaf Chowdhury

Figure 1 for Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates
Figure 2 for Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates
Figure 3 for Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates
Figure 4 for Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates

Oobleck enables resilient distributed training of large DNN models with guaranteed fault tolerance. It takes a planning-execution co-design approach, where it first generates a set of heterogeneous pipeline templates and instantiates at least $f+1$ logically equivalent pipeline replicas to tolerate any $f$ simultaneous failures. During execution, it relies on already-replicated model states across the replicas to provide fast recovery. Oobleck provably guarantees that some combination of the initially created pipeline templates can be used to cover all available resources after $f$ or fewer simultaneous failures, thereby avoiding resource idling at all times. Evaluation on large DNN models with billions of parameters shows that Oobleck provides consistently high throughput, and it outperforms state-of-the-art fault tolerance solutions like Bamboo and Varuna by up to $13.9x$.

* SOSP'23 | Camera-ready 
Viaarxiv icon

Depth analysis of battery performance based on a data-driven approach

Aug 30, 2023
Zhen Zhang, Hongrui Sun, Hui Sun

Figure 1 for Depth analysis of battery performance based on a data-driven approach
Figure 2 for Depth analysis of battery performance based on a data-driven approach
Figure 3 for Depth analysis of battery performance based on a data-driven approach
Figure 4 for Depth analysis of battery performance based on a data-driven approach

Capacity attenuation is one of the most intractable issues in the current of application of the cells. The disintegration mechanism is well known to be very complex across the system. It is a great challenge to fully comprehend this process and predict the process accurately. Thus, the machine learning (ML) technology is employed to predict the specific capacity change of the cell throughout the cycle and grasp this intricate procedure. Different from the previous work, according to the WOA-ELM model proposed in this work (R2 = 0.9999871), the key factors affecting the specific capacity of the battery are determined, and the defects in the machine learning black box are overcome by the interpretable model. Their connection with the structural damage of electrode materials and battery failure during battery cycling is comprehensively explained, revealing their essentiality to battery performance, which is conducive to superior research on contemporary batteries and modification.

Viaarxiv icon

Factor Graph Neural Networks

Aug 02, 2023
Zhen Zhang, Mohammed Haroon Dupty, Fan Wu, Javen Qinfeng Shi, Wee Sun Lee

Figure 1 for Factor Graph Neural Networks
Figure 2 for Factor Graph Neural Networks
Figure 3 for Factor Graph Neural Networks
Figure 4 for Factor Graph Neural Networks

In recent years, we have witnessed a surge of Graph Neural Networks (GNNs), most of which can learn powerful representations in an end-to-end fashion with great success in many real-world applications. They have resemblance to Probabilistic Graphical Models (PGMs), but break free from some limitations of PGMs. By aiming to provide expressive methods for representation learning instead of computing marginals or most likely configurations, GNNs provide flexibility in the choice of information flowing rules while maintaining good performance. Despite their success and inspirations, they lack efficient ways to represent and learn higher-order relations among variables/nodes. More expressive higher-order GNNs which operate on k-tuples of nodes need increased computational resources in order to process higher-order tensors. We propose Factor Graph Neural Networks (FGNNs) to effectively capture higher-order relations for inference and learning. To do so, we first derive an efficient approximate Sum-Product loopy belief propagation inference algorithm for discrete higher-order PGMs. We then neuralize the novel message passing scheme into a Factor Graph Neural Network (FGNN) module by allowing richer representations of the message update rules; this facilitates both efficient inference and powerful end-to-end learning. We further show that with a suitable choice of message aggregation operators, our FGNN is also able to represent Max-Product belief propagation, providing a single family of architecture that can represent both Max and Sum-Product loopy belief propagation. Our extensive experimental evaluation on synthetic as well as real datasets demonstrates the potential of the proposed model.

* Accepted by JMLR 
Viaarxiv icon