Kunpeng Zhang

Yiyou Sun, Xinyang Han, Weichen Zhang et al.

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 subfields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is 2.6%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP-relevant impact.

Kunpeng Zhang, Lan Wu, Liang Zheng et al.

Large-scale data missing is a challenging problem in Intelligent Transportation Systems (ITS). Many studies have been carried out to impute large-scale traffic data by considering their spatiotemporal correlations at a network level. In existing traffic data imputations, however, rich semantic information of a road network has been largely ignored when capturing network-wide spatiotemporal correlations. This study proposes a Graph Transformer for Traffic Data Imputation (GT-TDI) model to impute large-scale traffic data with spatiotemporal semantic understanding of a road network. Specifically, the proposed model introduces semantic descriptions consisting of network-wide spatial and temporal information of traffic data to help the GT-TDI model capture spatiotemporal correlations at a network level. The proposed model takes incomplete data, the social connectivity of sensors, and semantic descriptions as input to perform imputation tasks with the help of Graph Neural Networks (GNN) and Transformer. On the PeMS freeway dataset, extensive experiments are conducted to compare the proposed GT-TDI model with conventional methods, tensor factorization methods, and deep learning-based methods. The results show that the proposed GT-TDI outperforms existing methods in complex missing patterns and diverse missing rates. The code of the GT-TDI model will be available at https://github.com/KP-Zhang/GT-TDI.

Qiang Gao, Xinzhu Zhou, Kunpeng Zhang et al.

Stock selection attempts to rank a list of stocks for optimizing investment decision making, aiming at minimizing investment risks while maximizing profit returns. Recently, researchers have developed various (recurrent) neural network-based methods to tackle this problem. Without exceptions, they primarily leverage historical market volatility to enhance the selection performance. However, these approaches greatly rely on discrete sampled market observations, which either fail to consider the uncertainty of stock fluctuations or predict continuous stock dynamics in the future. Besides, some studies have considered the explicit stock interdependence derived from multiple domains (e.g., industry and shareholder). Nevertheless, the implicit cross-dependencies among different domains are under-explored. To address such limitations, we present a novel stock selection solution -- StockODE, a latent variable model with Gaussian prior. Specifically, we devise a Movement Trend Correlation module to expose the time-varying relationships regarding stock movements. We design Neural Recursive Ordinary Differential Equation Networks (NRODEs) to capture the temporal evolution of stock volatility in a continuous dynamic manner. Moreover, we build a hierarchical hypergraph to incorporate the domain-aware dependencies among the stocks. Experiments conducted on two real-world stock market datasets demonstrate that StockODE significantly outperforms several baselines, such as up to 18.57% average improvement regarding Sharpe Ratio.

Chengtai Cao, Fan Zhou, Yurou Dai et al.

Data augmentation (DA) is indispensable in modern machine learning and deep neural networks. The basic idea of DA is to construct new training data to improve the model's generalization by adding slightly disturbed versions of existing data or synthesizing new data. This survey comprehensively reviews a crucial subset of DA techniques, namely Mix-based Data Augmentation (MixDA), which generates novel samples by combining multiple examples. In contrast to traditional DA approaches that operate on single samples or entire datasets, MixDA stands out due to its effectiveness, simplicity, flexibility, computational efficiency, theoretical foundation, and broad applicability. We begin by introducing a novel taxonomy that categorizes MixDA into Mixup-based, Cutmix-based, and mixture approaches based on a hierarchical perspective of the data mixing operation. Subsequently, we provide an in-depth review of various MixDA techniques, focusing on their underlying motivations. Owing to its versatility, MixDA has penetrated a wide range of applications, which we also thoroughly investigate in this survey. Moreover, we delve into the underlying mechanisms of MixDA's effectiveness by examining its impact on model generalization and calibration while providing insights into the model's behavior by analyzing the inherent properties of MixDA. Finally, we recapitulate the critical findings and fundamental challenges of current MixDA studies while outlining the potential directions for future works. Different from previous related surveys that focus on DA approaches in specific domains (e.g., CV and NLP) or only review a limited subset of MixDA studies, we are the first to provide a systematical survey of MixDA, covering its taxonomy, methodology, application, and explainability. Furthermore, we provide promising directions for researchers interested in this exciting area.

Changrong Xiao, Wenxing Ma, Qingping Song et al.

Receiving timely and personalized feedback is essential for second-language learners, especially when human instructors are unavailable. This study explores the effectiveness of Large Language Models (LLMs), including both proprietary and open-source models, for Automated Essay Scoring (AES). Through extensive experiments with public and private datasets, we find that while LLMs do not surpass conventional state-of-the-art (SOTA) grading models in performance, they exhibit notable consistency, generalizability, and explainability. We propose an open-source LLM-based AES system, inspired by the dual-process theory. Our system offers accurate grading and high-quality feedback, at least comparable to that of fine-tuned proprietary LLMs, in addition to its ability to alleviate misgrading. Furthermore, we conduct human-AI co-grading experiments with both novice and expert graders. We find that our system not only automates the grading process but also enhances the performance and efficiency of human graders, particularly for essays where the model has lower confidence. These results highlight the potential of LLMs to facilitate effective human-AI collaboration in the educational context, potentially transforming learning experiences through AI-generated feedback.

Hanwen Shi, Jin Zhang, Kunpeng Zhang

Matching patients effectively and efficiently for clinical trials is a significant challenge due to the complexity and variability of patient profiles and trial criteria. This paper introduces \textbf{Multi-Agent for Knowledge Augmentation and Reasoning (MAKAR)}, a novel multi-agent system that enhances patient-trial matching by integrating criterion augmentation with structured reasoning. MAKAR consistently improves performance by an average of 7\% across different datasets. Furthermore, it enables privacy-preserving deployment and maintains competitive performance when using smaller open-source models. Overall, MAKAR can contributes to more transparent, accurate, and privacy-conscious AI-driven patient matching.

Zhonghao Li, Kunpeng Zhang, Jinghuai Ou et al.

Retrieval-augmented generation (RAG) systems face significant challenges in multi-hop question answering (MHQA), where complex queries require synthesizing information across multiple document chunks. Existing approaches typically rely on iterative LLM-based query rewriting and routing, resulting in high computational costs due to repeated LLM invocations and multi-stage processes. To address these limitations, we propose TreeHop, an embedding-level framework without the need for LLMs in query refinement. TreeHop dynamically updates query embeddings by fusing semantic information from prior queries and retrieved documents, enabling iterative retrieval through embedding-space operations alone. This method replaces the traditional "Retrieve-Rewrite-Vectorize-Retrieve" cycle with a streamlined "Retrieve-Embed-Retrieve" loop, significantly reducing computational overhead. Moreover, a rule-based stop criterion is introduced to further prune redundant retrievals, balancing efficiency and recall rate. Experimental results show that TreeHop rivals advanced RAG methods across three open-domain MHQA datasets, achieving comparable performance with only 5\%-0.4\% of the model parameter size and reducing the query latency by approximately 99\% compared to concurrent approaches. This makes TreeHop a faster and more cost-effective solution for deployment in a range of knowledge-intensive applications. For reproducibility purposes, codes and data are available here: https://github.com/allen-li1231/TreeHop-RAG.

Minghui Liu, Aadi Palnitkar, Tahseen Rabbani et al.

Large language models (LLMs) have demonstrated remarkable performance on long-context tasks, but are often bottlenecked by memory constraints. Namely, the KV cache, which is used to significantly speed up attention computations, grows linearly with context length. A suite of compression algorithms has been introduced to alleviate cache growth by evicting unimportant tokens. However, several popular strategies are targeted towards the prefill phase, i.e., processing long prompt context, and their performance is rarely assessed on reasoning tasks requiring long decoding. In particular, short but complex prompts, such as those in benchmarks like GSM8K and MATH500, often benefit from multi-step reasoning and self-reflection, resulting in thinking sequences thousands of tokens long. In this work, we benchmark the performance of several popular compression strategies on long-reasoning tasks. For the non-reasoning Llama-3.1-8B-Instruct, we determine that no singular strategy fits all, and that performance is heavily influenced by dataset type. However, we discover that H2O and our decoding-enabled variant of SnapKV are dominant strategies for reasoning models, indicating the utility of heavy-hitter tracking for reasoning traces. We also find that eviction strategies at low budgets can produce longer reasoning traces, revealing a tradeoff between cache size and inference costs.

Zhongyang Liu, Haoyu Pei, Xiangyi Xiao et al.

Due to the high value and high failure rate of startups, predicting their success has become a critical challenge across interdisciplinary research. Existing approaches typically model success prediction from the perspective of a single decision-maker, overlooking the collective dynamics of investor groups that dominate real-world venture capital (VC) decisions. In this paper, we propose SimVC-CAS, a novel collective agent system that simulates VC decision-making as a multi-agent interaction process. By designing role-playing agents and a GNN-based supervised interaction module, we reformulate startup financing prediction as a group decision-making task, capturing both enterprise fundamentals and the behavioral dynamics of potential investor networks. Each agent embodies an investor with unique traits and preferences, enabling heterogeneous evaluation and realistic information exchange through a graph-structured co-investment network. Using real-world data from PitchBook and under strict data leakage controls, we show that SimVC-CAS significantly improves predictive accuracy while providing interpretable, multiperspective reasoning, for example, approximately 25% relative improvement with respect to average precision@10. SimVC-CAS also sheds light on other complex group decision scenarios.

Haoyu Pei, Zhongyang Liu, Xiangyi Xiao et al.

Most venture capital (VC) investments fail, while a few deliver outsized returns. Accurately predicting startup success requires synthesizing complex relational evidence, including company disclosures, investor track records, and investment network structures, through explicit reasoning to form coherent, interpretable investment theses. Traditional machine learning and graph neural networks both lack this reasoning capability. Large language models (LLMs) offer strong reasoning but face a modality mismatch with graphs. Recent graph-LLM methods target in-graph tasks where answers lie within the graph, whereas VC prediction is off-graph: the target exists outside the network. The core challenge is selecting graph paths that maximize predictor performance on an external objective while enabling step-by-step reasoning. We present MIRAGE-VC, a multi-perspective retrieval-augmented generation framework that addresses two obstacles: path explosion (thousands of candidate paths overwhelm LLM context) and heterogeneous evidence fusion (different startups need different analytical emphasis). Our information-gain-driven path retriever iteratively selects high-value neighbors, distilling investment networks into compact chains for explicit reasoning. A multi-agent architecture integrates three evidence streams via a learnable gating mechanism based on company attributes. Under strict anti-leakage controls, MIRAGE-VC achieves +5.0% F1 and +16.6% PrecisionAt5, and sheds light on other off-graph prediction tasks such as recommendation and risk assessment. Code: https://anonymous.4open.science/r/MIRAGE-VC-323F.

Chujie Zheng, Kunpeng Zhang, Harry Jiannan Wang et al.

We introduce a new approach for abstractive text summarization, Topic-Guided Abstractive Summarization, which calibrates long-range dependencies from topic-level features with globally salient content. The idea is to incorporate neural topic modeling with a Transformer-based sequence-to-sequence (seq2seq) model in a joint learning framework. This design can learn and preserve the global semantics of the document, which can provide additional contextual guidance for capturing important ideas of the document, thereby enhancing the generation of summary. We conduct extensive experiments on two datasets and the results show that our proposed model outperforms many extractive and abstractive systems in terms of both ROUGE measurements and human evaluation. Our code is available at: https://github.com/chz816/tas.

Sun Xu, Tongkai Xu, Baiheng Xie et al.

Retrieval-Augmented Generation (RAG) has become a widely adopted paradigm for enhancing the reliability of large language models (LLMs). However, RAG systems are sensitive to retrieval strategies that rely on text chunking to construct retrieval units, which often introduce information fragmentation, retrieval noise, and reduced efficiency. Recent work has even questioned the necessity of RAG, arguing that long-context LLMs may eliminate multi-stage retrieval pipelines by directly processing full documents. Nevertheless, expanded context capacity alone does not resolve the challenges of relevance filtering, evidence prioritization, and isolating answer-bearing information. To this end, we proposed M-RAG, a novel Chunk-free retrieval strategy. Instead of retrieving coarse-grained textual chunks, M-RAG extracts structured, k-v decomposition meta-markers, with a lightweight, intent-aligned retrieval key for retrieval and a context-rich information value for generation. Under this setting, M-RAG enables efficient and stable query-key similarity matching without sacrificing expressive ability. Experimental results on the LongBench subtasks demonstrate that M-RAG outperforms chunk-based RAG baselines across varying token budgets, particularly under low-resource settings. Extensive analysis further reveals that M-RAG retrieves more answer-friendly evidence with high efficiency, validating the effectiveness of decoupling retrieval representation from generation and highlighting the proposed strategy as a scalable and robust alternative to existing chunk-based methods.

Xuewen Han, Neng Wang, Shangkun Che et al.

In recent years, the application of generative artificial intelligence (GenAI) in financial analysis and investment decision-making has gained significant attention. However, most existing approaches rely on single-agent systems, which fail to fully utilize the collaborative potential of multiple AI agents. In this paper, we propose a novel multi-agent collaboration system designed to enhance decision-making in financial investment research. The system incorporates agent groups with both configurable group sizes and collaboration structures to leverage the strengths of each agent group type. By utilizing a sub-optimal combination strategy, the system dynamically adapts to varying market conditions and investment scenarios, optimizing performance across different tasks. We focus on three sub-tasks: fundamentals, market sentiment, and risk analysis, by analyzing the 2023 SEC 10-K forms of 30 companies listed on the Dow Jones Index. Our findings reveal significant performance variations based on the configurations of AI agents for different tasks. The results demonstrate that our multi-agent collaboration system outperforms traditional single-agent models, offering improved accuracy, efficiency, and adaptability in complex financial environments. This study highlights the potential of multi-agent systems in transforming financial analysis and investment decision-making by integrating diverse analytical perspectives.

Kunpeng Zhang, Poppy Zhang, Shawndra Hill et al.

Video-based ads are a vital medium for brands to engage consumers, with social media platforms leveraging user data to optimize ad delivery and boost engagement. A crucial but under-explored aspect is the 'hooking period', the first three seconds that capture viewer attention and influence engagement metrics. Analyzing this brief window is challenging due to the multimodal nature of video content, which blends visual, auditory, and textual elements. Traditional methods often miss the nuanced interplay of these components, requiring advanced frameworks for thorough evaluation. This study presents a framework using transformer-based multimodal large language models (MLLMs) to analyze the hooking period of video ads. It tests two frame sampling strategies, uniform random sampling and key frame selection, to ensure balanced and representative acoustic feature extraction, capturing the full range of design elements. The hooking video is processed by state-of-the-art MLLMs to generate descriptive analyses of the ad's initial impact, which are distilled into coherent topics using BERTopic for high-level abstraction. The framework also integrates features such as audio attributes and aggregated ad targeting information, enriching the feature set for further analysis. Empirical validation on large-scale real-world data from social media platforms demonstrates the efficacy of our framework, revealing correlations between hooking period features and key performance metrics like conversion per investment. The results highlight the practical applicability and predictive power of the approach, offering valuable insights for optimizing video ad strategies. This study advances video ad analysis by providing a scalable methodology for understanding and enhancing the initial moments of video advertisements.

Kunpeng Zhang, Hanwen Xu, Sheng Wang

Deciphering tumor microenvironment from Whole Slide Images (WSIs) is intriguing as it is key to cancer diagnosis, prognosis and treatment response. While these gigapixel images on one hand offer a comprehensive portrait of cancer, on the other hand, the extremely large size, as much as more than 10 billion pixels, make it challenging and time-consuming to navigate to corresponding regions to support diverse clinical inspection. Inspired by pathologists who conducted navigation on WSIs with a combination of sampling, reasoning and self-reflection, we proposed "PathReasoning", a multi-modal reasoning agent that iteratively navigates across WSIs through multiple rounds of reasoning and refinements. Specifically, starting with randomly sampled candidate regions, PathReasoning reviews current selections with self-reflection, reasoning over the correspondence between visual observations and clinical questions, and concludes by proposing new regions to explore. Across rounds, PathReasoning builds a reasoning chain that gradually directs attention to diagnostically relevant areas. PathReasoning turns each whole slide into a sequence of question-guided views, allowing the model to efficiently find informative ROIs within a fixed number of steps, without the need for dense pixel-level annotations. PathReasoning can substantially outperform strong ROI-selection approaches by 6.7% and 3.1% of AUROC on subtyping and longitudinal analysis tasks. The high-quality ROIs further support accurate report generation on breast cancer, significantly outperforming the standard GPT-4o by 10% in accuracy. PathReasoning prioritizes question-specific regions and constructs interpretable reasoning chains, supporting efficient slide review, consistent diagnostic interpretations, comprehensive reporting, and evidence traceability in digital pathology.

Jianping Ye, Michel Wedel, Kunpeng Zhang

Text-to-Image Diffusion models excel at generating images from text prompts but often exhibit suboptimal alignment with content semantics, aesthetics, and human preferences. To address these limitations, this study proposes a novel parameter-efficient framework, Indirect Prompt Gradient Optimization (IPGO), for prompt-level diffusion model fine-tuning. IPGO enhances prompt embeddings by injecting continuously differentiable embeddings at the beginning and end of the prompt embeddings, leveraging low-rank structures with the flexibility and nonlinearity from rotations. This approach enables gradient-based optimization of injected embeddings under range, orthonormality, and conformity constraints, effectively narrowing the search space, promoting a stable solution, and ensuring alignment between the embeddings of the injected embeddings and the original prompt. Its extension IPGO+ adds a parameter-free cross-attention mechanism on the prompt embedding to enforce dependencies between the original prompt and the inserted embeddings. We conduct extensive evaluations through prompt-wise (IPGO) and prompt-batch (IPGO+) training using three reward models of image aesthetics, image-text alignment, and human preferences across three datasets of varying complexity. The results show that IPGO consistently outperforms SOTA benchmarks, including stable diffusion v1.5 with raw prompts, text-embedding-based methods (TextCraftor), training-based methods (DRaFT and DDPO), and training-free methods (DPO-Diffusion, Promptist, and ChatGPT-4o). Specifically, IPGO achieves a win-rate exceeding 99% in prompt-wise learning, and IPGO+ achieves a comparable, but often better performance against current SOTAs (a 75% win rate) in prompt-batch learning. Moreover, we illustrate IPGO's generalizability and its capability to significantly enhance image quality while requiring minimal data and resources.

Changrong Xiao, Sean Xin Xu, Kunpeng Zhang

Image captioning, an important vision-language task, often requires a tremendous number of finely labeled image-caption pairs for learning the underlying alignment between images and texts. In this paper, we proposed a multimodal data augmentation method, leveraging a recent text-to-image model called Stable Diffusion, to expand the training set via high-quality generation of image-caption pairs. Extensive experiments on the MS COCO dataset demonstrate the advantages of our approach over several benchmark methods, and particularly a significant boost when having fewer training instances. In addition, models trained on our augmented datasets also outperform prior unpaired image captioning methods by a large margin. Finally, further improvement regarding the training efficiency and effectiveness can be obtained after intentionally filtering the generated data based on quality assessment.

Kunpeng Zhang, Xi Xiao, Xiaogang Zhu et al.

Coverage-guided Greybox Fuzzing (CGF) is one of the most successful and widely-used techniques for bug hunting. Two major approaches are adopted to optimize CGF: (i) to reduce search space of inputs by inferring relationships between input bytes and path constraints; (ii) to formulate fuzzing processes (e.g., path transitions) and build up probability distributions to optimize power schedules, i.e., the number of inputs generated per seed. However, the former is subjective to the inference results which may include extra bytes for a path constraint, thereby limiting the efficiency of path constraints resolution, code coverage discovery, and bugs exposure; the latter formalization, concentrating on power schedules for seeds alone, is inattentive to the schedule for bytes in a seed. In this paper, we propose a lightweight fuzzing approach, Truzz, to optimize existing Coverage-guided Greybox Fuzzers (CGFs). To address two aforementioned challenges, Truzz identifies the bytes related to the validation checks (i.e., the checks guarding error-handling code), and protects those bytes from being frequently mutated, making most generated inputs examine the functionalities of programs, in lieu of being rejected by validation checks. The byte-wise relationship determination mitigates the problem of loading extra bytes when fuzzers infer the byte-constraint relation. Furthermore, the proposed path transition within Truzz can efficiently prioritize the seed as the new path, harvesting many new edges, and the new path likely belongs to a code region with many undiscovered code lines. The experimental results show that on average, Truzz can generate 16.14% more inputs flowing into functional code, in addition to 24.75% more new edges than the vanilla fuzzers. Finally, our approach exposes 13 bugs in 8 target programs, and 6 of them have not been identified by the vanilla fuzzers.

Qiang Gao, Wei Wang, Kunpeng Zhang et al.

Trip recommendation is a significant and engaging location-based service that can help new tourists make more customized travel plans. It often attempts to suggest a sequence of point of interests (POIs) for a user who requests a personalized travel demand. Conventional methods either leverage the heuristic algorithms (e.g., dynamic programming) or statistical analysis (e.g., Markov models) to search or rank a POI sequence. These procedures may fail to capture the diversity of human needs and transitional regularities. They even provide recommendations that deviate from tourists' real travel intention when the trip data is sparse. Although recent deep recursive models (e.g., RNN) are capable of alleviating these concerns, existing solutions hardly recognize the practical reality, such as the diversity of tourist demands, uncertainties in the trip generation, and the complex visiting preference. Inspired by the advance in deep learning, we introduce a novel self-supervised representation learning framework for trip recommendation -- SelfTrip, aiming at tackling the aforementioned challenges. Specifically, we propose a two-step contrastive learning mechanism concerning the POI representation, as well as trip representation. Furthermore, we present four trip augmentation methods to capture the visiting uncertainties in trip planning. We evaluate our SelfTrip on four real-world datasets, and extensive results demonstrate the promising gain compared with several cutting-edge benchmarks, e.g., up to 4% and 12% on F1 and pair-F1, respectively.

Chujie Zheng, Kunpeng Zhang, Harry Jiannan Wang et al.

In this paper, we present a denoising sequence-to-sequence (seq2seq) autoencoder via contrastive learning for abstractive text summarization. Our model adopts a standard Transformer-based architecture with a multi-layer bi-directional encoder and an auto-regressive decoder. To enhance its denoising ability, we incorporate self-supervised contrastive learning along with various sentence-level document augmentation. These two components, seq2seq autoencoder and contrastive learning, are jointly trained through fine-tuning, which improves the performance of text summarization with regard to ROUGE scores and human evaluation. We conduct experiments on two datasets and demonstrate that our model outperforms many existing benchmarks and even achieves comparable performance to the state-of-the-art abstractive systems trained with more complex architecture and extensive computation resources.

Xovee Xu, Fan Zhou, Kunpeng Zhang et al.

Supervised learning, while prevalent for information cascade modeling, often requires abundant labeled data in training, and the trained model is not easy to generalize across tasks and datasets. It often learns task-specific representations, which can easily result in overfitting for downstream tasks. Recently, self-supervised learning is designed to alleviate these two fundamental issues in linguistic and visual tasks. However, its direct applicability for information cascade modeling, especially graph cascade related tasks, remains underexplored. In this work, we present Contrastive Cascade Graph Learning (CCGL), a novel framework for information cascade graph learning in a contrastive, self-supervised, and task-agnostic way. In particular, CCGL first designs an effective data augmentation strategy to capture variation and uncertainty by simulating the information diffusion in graphs. Second, it learns a generic model for graph cascade tasks via self-supervised contrastive pre-training using both unlabeled and labeled data. Third, CCGL learns a task-specific cascade model via fine-tuning using labeled data. Finally, to make the model transferable across datasets and cascade applications, CCGL further enhances the model via distillation using a teacher-student architecture. We demonstrate that CCGL significantly outperforms its supervised and semi-supervised counterparts for several downstream tasks.

Shiwei Lyu, Shuai Ling, Kaihao Guo et al.

Predicting the start-ups that will eventually succeed is essentially important for the venture capital business and worldwide policy makers, especially at an early stage such that rewards can possibly be exponential. Though various empirical studies and data-driven modeling work have been done, the predictive power of the complex networks of stakeholders including venture capital investors, start-ups, and start-ups' managing members has not been thoroughly explored. We design an incremental representation learning mechanism and a sequential learning model, utilizing the network structure together with the rich attributes of the nodes. In general, our method achieves the state-of-the-art prediction performance on a comprehensive dataset of global venture capital investments and surpasses human investors by large margins. Specifically, it excels at predicting the outcomes for start-ups in industries such as healthcare and IT. Meanwhile, we shed light on impacts on start-up success from observable factors including gender, education, and networking, which can be of value for practitioners as well as policy makers when they screen ventures of high growth potentials.

Dongcheng Zhang, Kunpeng Zhang

Existing weighting methods for treatment effect estimation are often built upon the idea of propensity scores or covariate balance. They usually impose strong assumptions on treatment assignment or outcome model to obtain unbiased estimation, such as linearity or specific functional forms, which easily leads to the major drawback of model mis-specification. In this paper, we aim to alleviate these issues by developing a distribution learning-based weighting method. We first learn the true underlying distribution of covariates conditioned on treatment assignment, then leverage the ratio of covariates' density in the treatment group to that of the control group as the weight for estimating treatment effects. Specifically, we propose to approximate the distribution of covariates in both treatment and control groups through invertible transformations via change of variables. To demonstrate the superiority, robustness, and generalizability of our method, we conduct extensive experiments using synthetic and real data. From the experiment results, we find that our method for estimating average treatment effect on treated (ATT) with observational data outperforms several cutting-edge weighting-only benchmarking methods, and it maintains its advantage under a doubly-robust estimation framework that combines weighting with some advanced outcome modeling methods.

Chujie Zheng, Kunpeng Zhang, Harry Jiannan Wang et al.

Podcast summarization is different from summarization of other data formats, such as news, patents, and scientific papers in that podcasts are often longer, conversational, colloquial, and full of sponsorship and advertising information, which imposes great challenges for existing models. In this paper, we focus on abstractive podcast summarization and propose a two-phase approach: sentence selection and seq2seq learning. Specifically, we first select important sentences from the noisy long podcast transcripts. The selection is based on sentence similarity to the reference to reduce the redundancy and the associated latent topics to preserve semantics. Then the selected sentences are fed into a pre-trained encoder-decoder framework for the summary generation. Our approach achieves promising results regarding both ROUGE-based measures and human evaluations.

Chujie Zheng, Harry Jiannan Wang, Kunpeng Zhang et al.

Podcast summary, an important factor affecting end-users' listening decisions, has often been considered a critical feature in podcast recommendation systems, as well as many downstream applications. Existing abstractive summarization approaches are mainly built on fine-tuned models on professionally edited texts such as CNN and DailyMail news. Different from news, podcasts are often longer, more colloquial and conversational, and noisier with contents on commercials and sponsorship, which makes automatic podcast summarization extremely challenging. This paper presents a baseline analysis of podcast summarization using the Spotify Podcast Dataset provided by TREC 2020. It aims to help researchers understand current state-of-the-art pre-trained models and hence build a foundation for creating better models.

Fan Zhou, Xovee Xu, Goce Trajcevski et al.

The deluge of digital information in our daily life -- from user-generated content, such as microblogs and scientific papers, to online business, such as viral marketing and advertising -- offers unprecedented opportunities to explore and exploit the trajectories and structures of the evolution of information cascades. Abundant research efforts, both academic and industrial, have aimed to reach a better understanding of the mechanisms driving the spread of information and quantifying the outcome of information diffusion. This article presents a comprehensive review and categorization of information popularity prediction methods, from feature engineering and stochastic processes, through graph representation, to deep learning-based approaches. Specifically, we first formally define different types of information cascades and summarize the perspectives of existing studies. We then present a taxonomy that categorizes existing works into the aforementioned three main groups as well as the main subclasses in each group, and we systematically review cutting-edge research work. Finally, we summarize the pros and cons of existing research efforts and outline the open challenges and opportunities in this field.

Fan Zhou, Xovee Xu, Ce Li et al.

Quantifying and predicting the long-term impact of scientific writings or individual scholars has important implications for many policy decisions, such as funding proposal evaluation and identifying emerging research fields. In this work, we propose an approach based on Heterogeneous Dynamical Graph Neural Network (HDGNN) to explicitly model and predict the cumulative impact of papers and authors. HDGNN extends heterogeneous GNNs by incorporating temporally evolving characteristics and capturing both structural properties of attributed graph and the growing sequence of citation behavior. HDGNN is significantly different from previous models in its capability of modeling the node impact in a dynamic manner while taking into account the complex relations among nodes. Experiments conducted on a real citation dataset demonstrate its superior performance of predicting the impact of both papers and authors.

Fan Zhou, Chengtai Cao, Kunpeng Zhang et al.

Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to tackle few-shot learning problems such as image and text, in rather Euclidean domain. However, there are very few works applying meta-learning to non-Euclidean domains, and the recently proposed graph neural networks (GNNs) models do not perform effectively on graph few-shot learning problems. Towards this, we propose a novel graph meta-learning framework -- Meta-GNN -- to tackle the few-shot node classification problem in graph meta-learning settings. It obtains the prior knowledge of classifiers by training on many similar few-shot learning tasks and then classifies the nodes from new classes with only few labeled samples. Additionally, Meta-GNN is a general model that can be straightforwardly incorporated into any existing state-of-the-art GNN. Our experiments conducted on three benchmark datasets demonstrate that our proposed approach not only improves the node classification performance by a large margin on few-shot learning problems in meta-learning paradigm, but also learns a more general and flexible model for task adaption.