Time series forecasting has witnessed significant advancements through deep learning techniques. However, most existing methods struggle in non-stationary environments, where data distributions evolve over time due to concept drift. To address the challenge of non-stationarity in time series, various stabilization techniques have been proposed to mitigate temporal variations. Nonetheless, these methods operate at the instance level, assuming a homogeneous distribution across all time steps within an instance and relying on fixed statistical normalization. This limits their ability to effectively capture fine-grained distributional shifts.

The stock market is a complex and dynamic system, where it is non-trivial for researchers and practitioners to uncover underlying patterns and forecast stock movements. The existing studies for stock market analysis rely on leveraging various types of information to extract useful factors, which are highly conditional on the quality of the data used. However, the currently available resources are mainly based on the U.S. stock market in English, which is inapplicable to adapt to other countries. To address these issues, we propose CSMD, a multimodal dataset curated specifically for analyzing the Chinese stock market with meticulous processing for validated quality. In addition, we develop a lightweight and user-friendly framework LightQuant for researchers and practitioners with expertise in financial domains. Experimental results on top of our datasets and framework with various backbone models demonstrate their effectiveness compared with using existing datasets. The datasets and code are publicly available at the link: https://github.com/ECNU-CILAB/LightQuant.

Various real-world graphs, such as social and transaction networks, are typically distributed across users, each of whom holds a local view of the graph (i.e., their own relationships with others). Densest Subgraph Discovery (DSD) on such decentralized graphs is a fundamental task that can uncover valuable insights for downstream applications, including fraud detection, community identification, and user behavior mining. Additionally, in many scenarios, due to privacy concerns, sensitive original local views cannot be collected for DSD. Although there have been extensive studies on DSD, most existing algorithms either do not take user privacy into account or are specific to the centralized privacy setting that requires a (trusted) curator to collect all local views from users and then analyze the entire graph privately.

Federated learning (FL) is a privacy-preserving machine learning paradigm that enables collaborative model training across multiple distributed clients without disclosing their raw data. Personalized federated learning (pFL) has gained increasing attention for its ability to address data heterogeneity. However, most existing pFL methods assume that each client's data follows a single distribution and learn one client-level personalized model for each client. This assumption often fails in practice, where a single client may possess data from multiple sources or domains, resulting in significant intra-client heterogeneity and suboptimal performance. To tackle this challenge, we propose pFedBayesPT, a fine-grained instance-wise pFL framework based on visual prompt tuning. Specifically, we formulate instance-wise prompt generation from a Bayesian perspective and model the prompt posterior as an implicit distribution to capture diverse visual semantics. We derive a variational training objective under the semi-implicit variational inference framework. Extensive experiments on benchmark datasets demonstrate that pFedBayesPT consistently outperforms existing pFL methods under both feature and label heterogeneity settings.

Story visualization aims to create visual content, such as images and videos, that is consistent, coherent, and complete with a given story. Despite significant advances in the application of diffusion models for general text-to-image generation tasks, they still encounter difficulties when directly used to produce consistent visual content that accurately aligns with the narrative text. In this paper, we propose a novel training-free automated story visualization framework called AgentStory that can generate image illustrations based on a story synopsis provided by users. Specifically, the framework employs multiple agents empowered by Large Language Models (LLMs) to create detailed descriptions of each subject and scene in the entire story. Then, it integrates a masking mechanism with a fine-grained consistency refinement adapter to incorporate different subjects in a scene. Furthermore, it utilizes the visual understanding capabilities of multimodal LLMs to include detailed features of different subjects in the refinement adapter, thus improving the consistency of each subject across multiple scenes. Finally, we compare the AgentStory framework with state-of-the-art baselines for story visualization on the DS-500 dataset and demonstrate its superior performance in terms of subject consistency, text-image alignment, and aesthetic quality. Our code is publicly available at https://github.com/tc2000731/AgentStory.

The remarkable ability of diffusion models to generate high-fidelity images has led to their widespread adoption. However, concerns have also arisen regarding their potential to produce Not Safe for Work (NSFW) content and exhibit social biases, hindering their practical use in real-world applications. In response to this challenge, prior work has focused on employing security filters to identify and exclude toxic text, or alternatively, fine-tuning pre-trained diffusion models to erase sensitive concepts. Unfortunately, existing methods struggle to achieve satisfactory performance in the sense that they can have a significant impact on the normal model output while still failing to prevent the generation of harmful content in some cases. In this paper, we propose a novel self-discovery approach to identifying a semantic direction vector in the embedding space to restrict text embedding within a safe region. Our method circumvents the need for correcting individual words within the input text and steers the entire text prompt towards a safe region in the embedding space, thereby enhancing model robustness against all possibly unsafe prompts. In addition, we employ Low-Rank Adaptation (LoRA) for semantic direction vector initialization to reduce the impact on the model performance for other semantics. Furthermore, our method can also be integrated with existing methods to improve their social responsibility. Extensive experiments on benchmark datasets demonstrate that our method can effectively reduce NSFW content and mitigate social bias generated by diffusion models compared to several state-of-the-art baselines. WARNING:This paper contains model-generated images that may be potentially offensive.

The transferability of adversarial examples enables practical transfer-based attacks. However, existing theoretical analysis cannot effectively reveal what factors contribute to cross-model transferability. Furthermore, the assumption that the target model dataset is available together with expensive prices of training proxy models also leads to insufficient practicality. We first propose a novel frequency perspective to study the transferability and then identify two factors that impair the transferability: an unchangeable intrinsic difference term along with a controllable perturbation-related term. To enhance the transferability, an optimization task with the constraint that decreases the impact of the perturbation-related term is formulated and an approximate solution for the task is designed to address the intractability of Fourier expansion. To address the second issue, we suggest employing pre-trained models as proxy models, which are freely available. Leveraging these advancements, we introduce cost-effective transfer-based attack ( CTA ), which addresses the optimization task in pre-trained models. CTA can be unleashed against broad applications, at any time, with minimal effort and nearly zero cost to attackers. This remarkable feature indeed makes CTA an effective, versatile, and fundamental tool for attacking and understanding a wide range of target models, regardless of their architecture or training dataset used. Extensive experiments show impressive attack performance of CTA across various models trained in seven black-box domains, highlighting the broad applicability and effectiveness of CTA .

Hard-label black-box textual adversarial attack presents a challenging task where only the predictions of the victim model are available. Moreover, several constraints further complicate the task of launching such attacks, including the inherent discrete and non-differentiable nature of text data and the need to introduce subtle perturbations that remain imperceptible to humans while preserving semantic similarity. Despite the considerable research efforts dedicated to this problem, existing methods still suffer from several limitations. For example, algorithms based on complex heuristic searches necessitate extensive querying, rendering them computationally expensive. The introduction of continuous gradient strategies into discrete text spaces often leads to estimation errors. Meanwhile, geometry-based strategies are prone to falling into local optima. To address these limitations, in this paper, we introduce SGFL-Attack, a novel approach that leverages a Similarity-Guidance strategy based on Feedback Learning for hard-label textual adversarial attack, with limited query budget. Specifically, the proposed SGFL-Attack utilizes word embedding vectors to assess the importance of words and positions in text sequences, and employs a feedback learning mechanism to determine reward or punishment based on changes in predicted labels caused by replacing words. In each iteration, SGFL-Attack guides the search based on knowledge acquired from the feedback learning mechanism, generating more similar samples while maintaining low perturbations. Moreover, to reduce the query budget, we incorporate local hash mapping to avoid redundant queries during the search process. Extensive experiments on seven widely used datasets show that the proposed SGFL-Attack method significantly outperforms state-of-the-art baselines and defenses over multiple language models.

Textual adversarial attack in black-box scenarios is a challenging task, as only the predicted label is available, and the text space is discrete and non-differentiable. Current research in this area is still in its infancy and mostly focuses on untargeted attack, lacking the capability to control the labels of the generated adversarial examples. Meanwhile, existing textual adversarial attack methods primarily rely on word substitution operations to maintain semantic similarity between the adversarial and original examples, which greatly limits the search space for adversarial examples. To address these issues, we propose a novel Lexical-Syntactic Targeted Adversarial Attack method tailored for the black-box settings, referred to as LST2A. Our approach involves adversarial perturbations at different levels of granularities, i.e., word-level with word substitution operations and syntactic-level through rewriting the syntax of the examples. Specifically, we first embed the entire text into the embedding layer of a masked language model, and then optimize perturbations at the word level within the hidden state to generate adversarial examples with the target label. For examples that are difficult to attack successfully with only word-level perturbations at higher semantic similarity thresholds, we leverage Large Language Model (LLM) to introduce syntactic-level perturbations to these examples, making them more vulnerable to the decision boundary of the victim model. Subsequently, we re-optimize the word-level perturbations for these vulnerable examples. Extensive experiments and human evaluations demonstrate that our proposed method consistently outperforms the state-of-the-art baselines, crafting smoother, more grammatically correct adversarial examples.

The sliding window model of computation captures scenarios in which data are continually arriving in the form of a stream, and only the most recent w items are used for analysis. In this setting, an algorithm needs to accurately track some desired statistics over the sliding window using a small space. When data streams contain sensitive information about individuals, the algorithm is also urgently needed to provide a provable guarantee of privacy. In this paper, we focus on the two fundamental problems of privately (1) estimating the frequency of an arbitrary item and (2) identifying the most frequent items (i.e., heavy hitters), in the sliding window model. We propose DPSW-Sketch, a sliding window framework based on the count-min sketch that not only satisfies differential privacy over the stream but also approximates the results for frequency and heavy-hitter queries within bounded errors in sublinear time and space w.r.t. w. Extensive experiments on five real-world and synthetic datasets show that DPSW-Sketch provides significantly better utility-privacy trade-offs than state-of-the-art methods.

Self-attention-based vision transformers (ViTs) have emerged as a highly competitive architecture in computer vision. Unlike convo-lutional neural networks (CNNs), ViTs are capable of global information sharing. With the development of various structures of ViTs, ViTs are increasingly advantageous for many vision tasks. However, the quadratic complexity of self-attention renders ViTs computationally intensive, and their lack of inductive biases of locality and translation equivariance demands larger model sizes compared to CNNs to effectively learn visual features. In this paper, we propose a light-weight and efficient vision transformer model called DualToken-ViT that leverages the advantages of CNNs and ViTs. DualToken-ViT effectively fuses the token with local information obtained by convolution-based structure and the token with global information obtained by self-attention-based structure to achieve an efficient attention structure. In addition, we use position-aware global tokens throughout all stages to enrich the global information, which further strengthening the effect of DualToken-ViT. Position-aware global tokens also contain the position information of the image, which makes our model better for vision tasks. We conducted extensive experiments on image classification, object detection and semantic segmentation tasks to demonstrate the effectiveness of DualToken-ViT. On the ImageNet-1K dataset, our models of different scales achieve accuracies of 75.4% and 79.4% with only 0.5G and 1.0G FLOPs, respectively, and our model with 1.0G FLOPs outperforms LightViT-T using global tokens by 0.7%.

Personalized federated learning (pFL) has gained significant attention as a promising approach to address the challenge of data heterogeneity. In this paper, we address a relatively unexplored problem in federated learning. When a federated model has been trained and deployed, and an unla-beled new client joins, providing a personalized model for the new client becomes a highly challenging task. To address this challenge, we extend the adaptive risk minimization technique into the unsupervised pFL setting and propose our method, FedTTA. We further improve FedTTA with two simple yet highly effective optimization strategies: enhancing the training of the adaptation model with proxy regularization and early-stopping the adaptation through entropy. Moreover, we propose a knowledge distillation loss specifically designed for FedTTA to address the device heterogeneity. Extensive experiments on five datasets against eleven baselines demonstrate the effectiveness of our proposed FedTTA and its variants. The code is available at: https://github.com/anonymous-federated-learning/code.

Federated learning is a privacy-focused learning paradigm, which trains a global model with gradients uploaded from multiple participants, circumventing explicit exposure of private data. However, previous research of gradient leakage attacks suggests that gradients alone are sufficient to reconstruct private data, rendering the privacy protection mechanism of federated learning unreliable. Existing defenses commonly craft transformed gradients based on ground-truth gradients to obfuscate the attacks, but often are less capable of maintaining good model performance together with satisfactory privacy protection. In this paper, we propose a novel yet effective defense framework named guarding against gradient leakage (Guardian) that produces transformed gradients by jointly optimizing two theoretically-derived metrics associated with gradients for performance maintenance and privacy protection. In this way, the transformed gradients produced via Guardian can achieve minimal privacy leakage in theory with the given performance maintenance level. Moreover, we design an ingenious initialization strategy for faster generation of transformed gradients to enhance the practicality of Guardian in real-world applications, while demonstrating theoretical convergence of Guardian to the performance of the global model. Extensive experiments on various tasks show that, without sacrificing much accuracy, Guardian can effectively defend state-of-the-art gradient leakage attacks, compared with the slight effects of baseline defense approaches.

In federated learning (FL), malicious clients could manipulate the predictions of the trained model through backdoor attacks, posing a significant threat to the security of FL systems. Existing research primarily focuses on backdoor attacks and defenses within the generic federated learning scenario, where all clients collaborate to train a single global model. A recent study conducted by Qin et al. [ 24 ] marks the initial exploration of backdoor attacks within the personalized federated learning (pFL) scenario, where each client constructs a personalized model based on its local data. Notably, the study demonstrates that pFL methods with parameter decoupling can significantly enhance robustness against backdoor attacks. However, in this article, we whistleblow that pFL methods with parameter decoupling are still vulnerable to backdoor attacks. The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts. We analyze two direct causes of the heterogeneous classifiers: (1) data heterogeneity inherently exists among clients and (2) poisoning by malicious clients further exacerbates the data heterogeneity. To address these issues, we propose a two-pronged attack method, BapFL, which comprises two simple yet effective strategies: (1) poisoning only the feature encoder while keeping the classifier fixed and (2) diversifying the classifier through noise introduction to simulate that of the benign clients. Extensive experiments on three benchmark datasets under varying conditions demonstrate the effectiveness of our proposed attack. Additionally, we evaluate the effectiveness of six widely used defense methods and find that BapFL still poses a significant threat even in the presence of the best defense, Multi-Krum. We hope to inspire further research on attack and defense strategies in pFL scenarios. The code is available at: https://github.com/BapFL/code

Sales forecasting during the launch of new products has always been a challenging task, due to the lack of historical sales data. The dynamic market environment and consumer preferences also increase the uncertainty of predictions. Large chains face even greater difficulties due to their extensive presence across various regions. Traditional time-series forecasting methods usually rely on statistical models and empirical judgments, which are difficult to handle large, variable data and often fail to achieve satisfactory performance for new products. In this paper, we propose a Multi-granularity AdversaRial Learning framework (MARL) to leverage knowledge from old products and improve the quality of invariant representations for more accurate sales predictions. To evaluate our proposed method, we conducted extensive experiments on both a real-world dataset from a prominent international Café chain and a public dataset. The results demonstrated that our method is more effective than the existing state-of-the-art baselines for new product sales forecasting.

In recent years, diffusion models have become the most popular and powerful methods in the field of image synthesis, even rivaling human artists in artistic creativity. However, the key issue currently limiting the application of diffusion models is its extremely slow generation process. Although several methods were proposed to speed up the generation process, there still exists a trade-off between efficiency and quality. In this paper, we first provide a detailed theoretical and empirical analysis of the generation process of the diffusion models based on schedulers. We transform the designing problem of schedulers into the determination of several parameters, and further transform the accelerated generation process into an expansion process of the linear subspace. Based on these analyses, we consequently propose a novel method called Optimal Linear Subspace Search (OLSS), which accelerates the generation process by searching for the optimal approximation process of the complete generation process in the linear subspaces spanned by latent variables. OLSS is able to generate high-quality images with a very small number of steps. To demonstrate the effectiveness of our method, we conduct extensive comparative experiments on open-source diffusion models. Experimental results show that with a given number of steps, OLSS can significantly improve the quality of generated images. Using an NVIDIA A100 GPU, we make it possible to generate a high-quality image by Stable Diffusion within only one second without other optimization techniques.

Logistic regression is an algorithm widely used for binary classification in various real-world applications such as fraud detection, medical diagnosis, and recommendation systems. However, training a logistic regression model with data from different parties raises privacy concerns. Secure Multi-Party Computation (MPC) is a cryptographic tool that allows multiple parties to train a logistic regression model jointly without compromising privacy. The efficiency of the online training phase becomes crucial when dealing with large-scale data in practice. In this paper, we propose an online efficient protocol for privacy-preserving logistic regression based on Function Secret Sharing (FSS). Our protocols are designed in the two non-colluding servers setting and assume the existence of a third-party dealer who only poses correlated randomness to the computing parties. During the online phase, two servers jointly train a logistic regression model on their private data by utilizing pre-generated correlated randomness. Furthermore, we propose accurate and MPC-friendly alternatives to the sigmoid function and encapsulate the logistic regression training process into a function secret sharing gate. The online communication overhead significantly decreases compared with the traditional secure logistic regression training based on secret sharing. We provide both theoretical and experimental analyses to demonstrate the efficiency and effectiveness of our method.

With the explosive growth of video and text data on the web, text-video retrieval has become a vital task for online video platforms. Recently, text-video retrieval methods based on pre-trained models have attracted a lot of attention. However, existing methods cannot effectively capture the fine-grained information in videos, and typically suffer from the hubness problem where a collection of similar videos are retrieved by a large number of different queries. In this paper, we propose Match4Match, a new text-video retrieval method based on CLIP (Contrastive Language-Image Pretraining) and graph optimization theories. To balance calculation efficiency and model accuracy, Match4Match seamlessly supports three inference modes for different application scenarios. In fast vector retrieval mode, we embed texts and videos in the same space and employ a vector retrieval engine to obtain the top K videos. In fine-grained alignment mode, our method fully utilizes the pre-trained knowledge of the CLIP model to align words with corresponding video frames, and uses the fine-grained information to compute text-video similarity more accurately. In flow-style matching mode, to alleviate the detrimental impact of the hubness problem, we model the retrieval problem as a combinatorial optimization problem and solve it using maximum flow with minimum cost algorithm. To demonstrate the effectiveness of our method, we conduct experiments on five public text-video datasets. The overall performance of our proposed method outperforms state-of-the-art methods. Additionally, we evaluate the computational efficiency of Match4Match. Benefiting from the three flexible inference modes, Match4Match can respond to a large number of query requests with low latency or achieve high recall with acceptable time consumption.

With the rapid development of the Internet of Things (IoT), the need to expand the amount of data through data-sharing to improve the model performance of edge devices has become increasingly compelling. To effectively protect data privacy while leveraging data across silos, federated learning has emerged. However, in the real world applications, federated learning inevitably faeces both data and model heterogeneity challenges. To address the heterogeneity issues in federated networks, in this work, we seek to jointly learn a global feature representation that is robust across clients and potentially also generalizable to new clients. More specifically, we propose a personalized Federated optimization framework with Meta Critic (FedMC) that efficiently captures robust and generalizable domain-invariant knowledge across clients. Extensive experiments on four public datasets show that the proposed FedMC outperforms the competing state-of-the-art methods in heterogeneous federated learning settings. We have also performed detailed ablation analysis on the importance of different components of the proposed model.

Algorithmic trading is a crucial yet challenging task in the financial domain, where trading decisions are made sequentially from milliseconds to days based on the historical price movements and trading frequency. To model such a sequential decision making process in the dynamic financial markets, Deep Reinforcement Learning (DRL) based methods have been applied and demonstrated their success in finding trading strategies that achieve profitable returns. However, the financial markets are complex imperfect information games with high-level of noise and uncertainties which usually make the exploration policy of DRL less effective. In this paper, we propose an end-to-end DRL method that explores solutions on the whole graph via a probabilistic dynamic programming algorithm. Specifically, we separate the state into environment state and position state, and model the position state transition as a directed acyclic graph. To obtain reliable gradients for model training, we adopt a probabilistic dynamic programming algorithm to explore solutions over the whole graph instead of sampling a path. By avoiding the sampling procedure, we propose an efficient training algorithm and overcome the efficiency problem in most existing DRL methods. Furthermore, our method is compatible with most recurrent neural network architecture, which makes our method easy to implement and very effective in practice. Extensive experiments have been conducted on two real-world stock datasets. Experimental results demonstrate that our method can generate stable trading strategies for both high-frequency and low-frequency trading, significantly outperforming the baseline DRL methods on annualized return and Sharpe ratio.

Programming-based Pre-trained Language Models (PPLMs) such as CodeBERT have achieved great success in many downstream code-related tasks. Since the memory and computational complexity of self-attention in the Transformer grow quadratically with the sequence length, PPLMs typically limit the code length to 512. However, codes in real-world applications are generally long, such as code searches, which cannot be processed efficiently by existing PPLMs. To solve this problem, in this paper, we present SASA, a Structure-Aware Sparse Attention mechanism, which reduces the complexity and improves performance for long code understanding tasks. The key components in SASA are top-k sparse attention and Abstract Syntax Tree (AST)-based structure-aware attention. With top-k sparse attention, the most crucial attention relation can be obtained with a lower computational cost. As the code structure represents the logic of the code statements, which is a complement to the code sequence characteristics, we further introduce AST structures into attention. Extensive experiments on CodeXGLUE tasks show that SASA achieves better performance than the competing baselines.

Deep Neural Networks (DNNs) have achieved remarkable progress in various real-world applications, especially when abundant training data are provided. However, data isolation has become a serious problem currently. Existing works build privacy-preserving DNN models from either algorithmic perspective or cryptographic perspective. The former mainly splits the DNN computation graph between data holders or between data holders and server, which demonstrates good scalability but suffers from accuracy loss and potential privacy risks. In contrast, the latter leverages time-consuming cryptographic techniques, which has strong privacy guarantee but poor scalability. In this article, we propose SPNN—a Scalable and Privacy-preserving deep Neural Network learning framework, from an algorithmic-cryptographic co-perspective. From algorithmic perspective, we split the computation graph of DNN models into two parts, i.e., the private-data-related computations that are performed by data holders and the rest heavy computations that are delegated to a semi-honest server with high computation ability. From cryptographic perspective, we propose using two types of cryptographic techniques, i.e., secret sharing and homomorphic encryption, for the isolated data holders to conduct private-data-related computations privately and cooperatively. Furthermore, we implement SPNN in a decentralized setting and introduce user-friendly APIs. Experimental results conducted on real-world datasets demonstrate the superiority of our proposed SPNN.

Information-seeking conversation systems are increasingly popular in real-world applications, especially for e-commerce companies. To retrieve appropriate responses for users, it is necessary to compute the matching degrees between candidate responses and users' queries with historical dialogue utterances. As the contexts are usually much longer than responses, it is thus necessary to expand the responses (usually short) with richer information. Recent studies on pseudo-relevance feedback (PRF) have demonstrated its effectiveness in query expansion for search engines, hence we consider expanding response using PRF information. However, existing PRF approaches are either based on heuristic rules or require heavy manual labeling, which are not suitable for solving our task. To alleviate this problem, we treat the PRF selection for response expansion as a learning task and propose a reinforced learning method that can be trained in an end-to-end manner without any human annotations. More specifically, we propose a reinforced selector to extract useful PRF terms to enhance response candidates and a BERT-based response ranker to rank the PRF-enhanced responses. The performance of the ranker serves as a reward to guide the selector to extract useful PRF terms, which boosts the overall task performance. Extensive experiments on both standard benchmarks and commercial datasets prove the superiority of our reinforced PRF term selector compared with other potential soft or hard selection methods. Both case studies and quantitative analysis show that our model is capable of selecting meaningful PRF terms to expand response candidates and also achieving the best results compared with all baselines on a variety of evaluation metrics. We have also deployed our method on online production in an e-commerce company, which shows a significant improvement over the existing online ranking system.

The literature has witnessed the success of leveraging Pre-trained Language Models (PLMs) and Transfer Learning (TL) algorithms to a wide range of Natural Language Processing (NLP) applications, yet it is not easy to build an easy-to-use and scalable TL toolkit for this purpose. To bridge this gap, the EasyTransfer platform is designed to develop deep TL algorithms for NLP applications. EasyTransfer is backended with a high-performance and scalable engine for efficient training and inference, and also integrates comprehensive deep TL algorithms, to make the development of industrial-scale TL applications easier. In EasyTransfer, the built-in data and model parallelism strategies, combined with AI compiler optimization, show to be 4.0x faster than the community version of distributed training. EasyTransfer supports various NLP models in the ModelZoo, including mainstream PLMs and multi-modality models. It also features various in-house developed TL algorithms, together with the AppZoo for NLP applications. The toolkit is convenient for users to quickly start model training, evaluation, and online deployment. EasyTransfer is currently deployed at Alibaba to support a variety of business scenarios, including item recommendation, personalized search, conversational question answering, etc. Extensive experiments on real-world datasets and online applications show that EasyTransfer is suitable for online production with cutting-edge performance for various applications. The source code of EasyTransfer is released at Github1.

Question Answering (QA) systems have been extensively studied in both academia and the research community due to their wide real-world applications. When building such industrial-scale QA applications, we are facing two prominent challenges, i.e., i) lacking a sufficient amount of training data to learn an accurate model and ii) requiring high inference speed for online model serving. There are generally two ways to mitigate the above-mentioned problems. One is to adopt transfer learning to leverage information from other domains; the other is to distill the “dark knowledge” from a large teacher model to small student models. The former usually employs parameter sharing mechanisms for knowledge transfer, but does not utilize the “dark knowledge” of pre-trained large models. The latter usually does not consider the cross-domain information from other domains. We argue that these two types of methods can be complementary to each other. Hence in this work, we provide a new perspective on the potential of the teacher-student paradigm facilitating cross-domain transfer learning, where the teacher and student tasks belong to heterogeneous domains, with the goal to improve the student model’s performance in the target domain. Our framework considers the “dark knowledge” learned from large teacher models and also leverages the adaptive hints to alleviate the domain differences between teacher and student models. Extensive experiments have been conducted on two text matching tasks for retrieval-based QA systems. Results show the proposed method has better performance than the competing methods including the existing state-of-the-art transfer learning methods. We have also deployed our method in an online production system and observed significant improvements compared to the existing approaches in terms of both accuracy and cross-domain robustness.

With the rapid growth of data volume, data-driven machine learning models have become a necessary part of many industrial applications. Intuitively, the more high-quality data used for training leads to better model performance. However, in reality, data are usually scattered and isolated in different organizations or companies. Such a "data isolation" problem stimulates both academia and industry to explore the collaborative learning paradigm to build better models jointly with multiple data sources. Despite the potential performance gains, this learning paradigm inevitably faces privacy issues, especially for the Fintech domain where data are sensitive by nature. In this paper, we present a privacy-preserving collaborative learning system in Ant Financial, named Nebula. Our system aims to facilitate privacy-preserving collaborative model training for industrial-scale applications. Our system is built upon a ring-allreduce MPI based distributed framework. On top of that, with some optimization strategies and novel sharing scheme, our system is able to scale up to tens of millions of data samples with hundreds of thousands of features and achieve more than 100x speedup compared with the existing state-of-the-art implementations.

As one of the core components of customer service bot, User Intent Prediction (UIP) aims at predicting users? intents (usually represented as predefined user questions) before they ask, and has been widely applied in real applications. However, when developing a machine learning system for this problem, two critical issues, i.e., the problem of feature drift and class imbalance, may emerge and seriously deprave the system performance. Moreover, various scenarios may arise due to business demands, making the aforementioned problems much more severe. To address these two problems, we propose an attention-based Deep Multi-instance Sequential Cross Network (aDMSCN) to deal with the UIP task. On the one hand,the UIP task can be subtly formalized as multi-instance learning(MIL) task with an attention-based method proposed to alleviate the influences of feature drift. To the best of our knowledge, this is the first attempt to model the problem from a MIL perspective.On the other hand, a ratio-sensitive loss is also developed in our model, which can mitigate the negative impact of class imbalance. Extensive experiments on both offline real-world datasets and on-line A/B testing show that our proposed framework significantly out performs other state-of-art methods for the UIP task.

Conversational search is one of the ultimate goals of information retrieval. Recent research approaches conversational search by simplified settings of response ranking and conversational question answering, where an answer is either selected from a given candidate set or extracted from a given passage. These simplifications neglect the fundamental role of retrieval in conversational search. To address this limitation, we introduce an open-retrieval conversational question answering (ORConvQA) setting, where we learn to retrieve evidence from a large collection before extracting answers, as a further step towards building functional conversational search systems. We create a dataset, OR-QuAC, to facilitate research on ORConvQA. We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers. Our extensive experiments on OR-QuAC demonstrate that a learnable retriever is crucial for ORConvQA. We further show that our system can make a substantial improvement when we enable history modeling in all system components. Moreover, we show that the reranker component contributes to the model performance by providing a regularization effect. Finally, further in-depth analyses are performed to provide new insights into ORConvQA.

Personal assistant systems, such as Apple Siri, Google Assistant, Amazon Alexa, and Microsoft Cortana, are becoming ever more widely used. Understanding user intent such as clarification questions, potential answers and user feedback in information-seeking conversations is critical for retrieving good responses. In this paper, we analyze user intent patterns in information-seeking conversations and propose an intent-aware neural response ranking model “IART”, which refers to “Intent-Aware Ranking with Transformers”. IART is built on top of the integration of user intent modeling and language representation learning with the Transformer architecture, which relies entirely on a self-attention mechanism instead of recurrent nets [35]. It incorporates intent-aware utterance attention to derive an importance weighting scheme of utterances in conversation context with the aim of better conversation history understanding. We conduct extensive experiments with three information-seeking conversation data sets including both standard benchmarks and commercial data. Our proposed model outperforms all baseline methods with respect to a variety of metrics. We also perform case studies and analysis of learned user intent and its impact on response ranking in information-seeking conversations to provide interpretation of results.

The insurance industry has been creating innovative products around the emerging online shopping activities. Such ecommerce insurance is designed to protect buyers from potential risks such as impulse purchases and counterfeits. Fraudulent claims towards online insurance typically involve multiple parties such as buyers, sellers, and express companies, and they could lead to heavy financial losses. In order to uncover the relations behind organized fraudsters and detect fraudulent claims, we developed a large-scale insurance fraud detection system, i.e., InfDetect, which provides interfaces for commonly used graphs, standard data processing procedures, and a uniform graph learning platform. InfDetect is able to process big graphs containing up to 100 millions of nodes and billions of edges.In this paper, we investigate different graphs to facilitate fraudster mining, such as a device-sharing graph, a transaction graph, a friendship graph, and a buyer-seller graph. These graphs are fed to a uniform graph learning platform containing supervised and unsupervised graph learning algorithms. Cases on widely applied e-commerce insurance are described to demonstrate the usage and capability of our system. InfDetect has successfully detected thousands of fraudulent claims and saved over tens of thousands of dollars daily.

Product search and recommendation is a task that every e-commerce platform wants to outperform their peels on. However, training a good search or recommendation model often requires more data than what many platforms have. Fortunately, the search tasks on different platforms share the common underlying structure. Considering each platform as a domain, we propose a cross-domain learning approach to help the task on data-deficient platforms by leveraging the data from data-abundant platforms. In our solution, the importance of features in different domains is addressed by a domain-specific attention network. Meanwhile, a multi-task regularizer based on Wasserstein distance is introduced to help extract both domain-invariant and domain-specific features. Our model consistently outperforms the competing methods on both public and real-world industry datasets. Quantitative evaluation shows that our model can discover important features for different domains, which helps us better understand different user needs across platforms. Last but not least, we have deployed our model online in three big e-commerce platforms namely Taobao, Tmall, and Qintao, and observed better performance than the production models for all the platforms.

Conversational question answering (ConvQA) is a simplified but concrete setting of conversational search. One of its major challenges is to leverage the conversation history to understand and answer the current question. In this work, we propose a novel solution for ConvQA that involves three aspects. First, we propose a positional history answer embedding method to encode conversation history with position information using BERT in a natural way. BERT is a powerful technique for text representation. Second, we design a history attention mechanism (HAM) to conduct a "soft selection" for conversation histories. This method attends to history turns with different weights based on how helpful they are on answering the current question. Third, in addition to handling conversation history, we take advantage of multi-task learning (MTL) to do answer prediction along with another essential conversation task (dialog act prediction) using a uniform model architecture. MTL is able to learn more expressive and generic representations to improve the performance of ConvQA. We demonstrate the effectiveness of our model with extensive experimental evaluations on QuAC, a large-scale ConvQA dataset. We show that position information plays an important role in conversation history modeling. We also visualize the history attention and provide new insights into conversation history understanding.

A customer service bot is now a necessary component of an e-commerce platform. As a core module of the customer service bot, user intent prediction can help predict user questions before they ask. A typical solution is to find top candidate questions that a user will be interested in. Such solution ignores the inter-relationship between questions and often aims to maximize the immediate reward such as clicks, which may not be ideal in practice. Hence, we propose to view the problem as a sequential decision making process to better capture the long-term effects of each recommendation in the list. Intuitively, we formulate the problem as a Markov decision process and consider using reinforcement learning for the problem. With this approach, questions presented to users are both relevant and diverse. Experiments on offline real-world dataset and online system demonstrate the effectiveness of our proposed approach.

Consumers today face too many reviews to read when shopping online. Presenting the most helpful reviews, instead of all, to them will greatly ease purchase decision making. Most of the existing studies on review helpfulness prediction focused on domains with rich labels, not suitable for domains with insufficient labels. In response, we explore a multi-domain approach that learns domain relationships to help the task by transferring knowledge from data-rich domains to data-deficient domains. To better model domain differences, our approach gates multi-granularity embeddings in a Neural Network (NN) based transfer learning framework to reflect the domain-variant importance of words. Extensive experiments empirically demonstrate that our model outperforms the state-of-the-art baselines and NN-based methods without gating on this task. Our approach facilitates more effective knowledge transfer between domains, especially when the target domain dataset is small. Meanwhile, the domain relationship and domain-specific embedding gating are insightful and interpretable.

With the explosive growth of e-commerce and the booming of e-payment, detecting online transaction fraud in real time has become increasingly important to Fintech business. To tackle this problem, we introduce the TitAnt, a transaction fraud detection system deployed in Ant Financial, one of the largest Fintech companies in the world. The system is able to predict online real-time transaction fraud in mere milliseconds. We present the problem definition, feature extraction, detection methods, implementation and deployment of the system, as well as empirical effectiveness. Extensive experiments have been conducted on large real-world transaction data to show the effectiveness and the efficiency of the proposed system.

In this article, we investigate effective ways of utilizing crowdworkers in providing various urban services. The task recommendation platform that we design can match tasks to crowdworkers based on workers’ historical trajectories and time budget limits, thus making recommendations personal and efficient. One major challenge we manage to address is the handling of crowdworker’s trajectory uncertainties. In this article, we explicitly allow multiple routine routes to be probabilistically associated with each worker. We formulate this problem as an integer linear program whose goal is to maximize the expected total utility achieved by all workers. We further exploit the separable structures of the formulation and apply the Lagrangian relaxation technique to scale up computation. Numerical experiments have been performed over the instances generated using the realistic public transit dataset in Singapore. The results show that we can find significantly better solutions than the deterministic formulation, and in most cases we can find solutions that are very close to the theoretical performance limit. To demonstrate the practicality of our approach, we deployed our recommendation engine to a campus-scale field trial, and we demonstrate that workers receiving our recommendations incur fewer detours and complete more tasks, and are more efficient against workers relying on their own planning (25% more for top workers who receive recommendations). This is achieved despite having highly uncertain worker trajectories. We also demonstrate how to further improve the robustness of the system by using a simple multi-coverage mechanism.

We investigate the problem of large-scale mobile crowd-tasking, where a large pool of citizen crowd-workers are used to perform a variety of location-specific urban logistics tasks. Current approaches to such mobile crowd-tasking are very decentralized: a crowd-tasking platform usually provides each worker a set of available tasks close to the worker's current location; each worker then independently chooses which tasks she wants to accept and perform. In contrast, we propose TRACCS, a more coordinated task assignment approach, where the crowd-tasking platform assigns a sequence of tasks to each worker, taking into account their expected location trajectory over a wider time horizon, as opposed to just instantaneous location. We formulate such task assignment as an optimization problem, that seeks to maximize the total payoff from all assigned tasks, subject to a maximum bound on the detour (from the expected path) that a worker will experience to complete her assigned tasks. We develop credible computationally-efficient heuristics to address this optimization problem (whose exact solution requires solving a complex integer linear program), and show, via simulations with realistic topologies and commuting patterns, that a specific heuristic (called Greedy-ILS) increases the fraction of assigned tasks by more than 20%, and reduces the average detour overhead by more than 60%, compared to the current decentralized approach.