Modern recommendation platforms frequently encompass multiple domains to cater to the varied preferences of users. Recently, cross-domain learning has gained traction as a significant paradigm within the context of recommendation systems, enabling the leveraging of rich information from a well-endowed source domain to enhance a target domain, often limited by inadequate data resources. A primary concern in cross-domain recommendation is the mitigation of negative transfer-ensuring the selective transference of pertinent knowledge from the source (domain-shared knowledge) while maintaining the integrity of domain-unique insights within the target domain (domain-specific knowledge). In this paper, we propose a novel Disentangle-based Distillation Framework for Cross-Domain Recommendation (DDCDR), designed to operate at the representational level and rooted in the established teacher-student knowledge distillation paradigm. Our methodology begins with the development of a cross-domain teacher model, trained adversarially alongside a domain discriminator. This is followed by the creation of a target domain-specific student model. By employing the trained domain discriminator, we successfully segregate domain-shared from domain-specific representations. The teacher model guides the learning of domain-shared features, while domain-specific features are enhanced via contrastive learning methods. Experiments conducted on both public datasets and an industrial dataset demonstrate DDCDR achieves a new state-of-the-art performance. The implementation within Ant Group's platform further confirms its online efficacy, manifesting relative improvements of 0.33% and 0.45% in Unique Visitor Click-Through Rate (UVCTR) across two distinct recommendation scenarios, compared to baseline performances.
论文检索
输入标题、作者或关键词，从 642 篇学术成果中精准定位
In this paper, we tackle the complex task of analyzing televised debates, with a focus on a prime time news debate show from India. Previous methods, which often relied solely on text, fall short in capturing the multimodal essence of these debates [27]. To address this gap, we introduce a comprehensive automated toolkit that employs advanced computer vision and speech-to-text techniques for large-scale multimedia analysis. Utilizing state-of-the-art computer vision algorithms and speech-to-text methods, we transcribe, diarize, and analyze thousands of YouTube videos of a prime-time television debate show in India. These debates are a central part of Indian media but have been criticized for compromised journalistic integrity and excessive dramatization [18]. Our toolkit provides concrete metrics to assess bias and incivility, capturing a comprehensive multimedia perspective that includes text, audio utterances, and video frames. Our findings reveal significant biases in topic selection and panelist representation, along with alarming levels of incivility. This work offers a scalable, automated approach for future research in multimedia analysis, with profound implications for the quality of public discourse and democratic debate. To catalyze further research in this area, we also release the code, dataset collected and supplemental pdf.1
Dynamic Pricing for online retail has been discussed extensively in literature. However, past solutions fell short of addressing the unique challenges of independent multi-retailer platforms for grocery delivery. From limited visibility of retailers' inventories to diverse demand-side dynamics across retail brands and locations, the highly decentralized nature of multi-retailer platforms deviates from the classical framework of modeling price elasticity and cross-elasticity of demand. In this paper, we present a novel scheme to scalable and practical price adjustment in the highly dynamic multi-retailer context. First, we present a deep learning framework to distinctly model complex cross-elasticity relationships via additive neural networks augmented with adversarial data. Second, we present evolutionary optimization agents for adjusting itemized prices in a location-decentralized manner, while adhering to custom business constraints and objectives. The optimization utilizes the genetic algorithm structure, where we introduce a potential mechanism, inspired by bandit algorithms, in order to improve convergence speed by managing exploitation and exploration trade-offs. Our solution is deployed at Shipt and is extendable to other types of multi-retailer platforms, such as restaurant delivery. Finally, we empirically demonstrate performance using public and industry datasets of hundreds and thousands of diverse products across tens of stores, offering an optimization targets coverage scale in the tens of thousands, far larger than experimental setups in past research.
The impact of generative AI on e-commerce is profound. It has significantly improved the understanding of user intent and serves as a comprehensive product knowledge graph. However, the most substantial disruptions are yet to come, partic- ularly through the rise of autonomous agents. In this talk, I will outline a tentative path toward a future where e-commerce not only offers an unparalleled customer experience but also thrives in a world dominated by generative AI and autonomous agents.
Much of the world's most valued data is stored in relational databases and data warehouses, where the data is organized into many tables connected by primary-foreign key relations. However, building machine learning models using this data is both challenging and time consuming. The core problem is that no machine learning method is capable of learning on multiple tables interconnected by primary-foreign key relations. Current methods can only learn from a single table, so the data must first be manually joined and aggregated into a single training table, the process known as feature engineering. Feature engineering is slow, error prone and leads to suboptimal models. At Kumo.ai we have worked with researchers worldwide to develop an end-to-end deep representation learning approach to directly learn on data laid out across multiple tables [1]. We name our approach Relational Deep Learning (RDL). The core idea is to view relational databases as a temporal, heterogeneous graph, with a node for each row in each table, and edges specified by primary-foreign key links. Message Passing Graph Neural Networks can then automatically learn across the graph to extract representations that leverage all input data, without any manual feature engineering. Our relational deep learning method to encode graph structure into low-dimensional embeddings brings several benefits: (1) automatic learning from the entire data spread across multiple relational tables (2) no manual feature engineering as the system learns optimal embeddings for a target problem; (3) state-of-the-art predictive performance.
Population aging, increasing social demands, and rising costs of treatments are stressing healthcare systems to the point of risking the sustainability of universal and accessible healthcare. A hope in this dismal panorama is that there are large inefficiencies, and so opportunities for getting more from the same resources. To name a few, avoidable hospitalizations, unnecessary medication and tests, and lack of coordination among healthcare agents are estimated to cost several hundred billion euros per year in the EU. Technology can be useful for locating and reducing these inefficiencies, and within technology, the full exploitation of the data that the system collects to record its activity. In this talk, I will review the case for activity data analytics in healthcare, with two main considerations: 1) The need to include information about resources and costs in the models, in addition to clinical knowledge and patient outcomes, and 2) the need to use mostly data that healthcare organizations already collect and is not locked and distributed in silos. Fortunately, data collected for administrative and billing purposes, even though imperfect, partial, and low resolution, can be used to improve efficiency and safety, as well as fairness and equity. I will focus on the work carried out at Amalfi Analytics, a spin-off of my research group at UPC in Barcelona. On the one hand, we have addressed predictive management in hospitals, from influx to the emergency room to availability of surgical areas, beds, and staff. Anticipating activity, needs, and resource availability lets managers improve critical KPIs, e.g. waiting times, but also reduce staff stress, which leads to fewer medical errors and accidents. On the other hand, we have developed a patient cohort analyzer, based mostly on a recent clustering algorithm, that gives experts a fresh view of their patient population and lets them refine protocols and identify high-risk patient groups. This tool has also been used to support territorial planning and resource allocation. These problems have been extensively addressed in the past, but actual penetration of solutions in hospitals is smaller than one could expect. For example, one can find hundreds of papers on predicting influx to emergency rooms or bed demands, but many of them conclude after producing an AUC figure, and even fewer describe a working system that can be exported from the hospital where they were developed to others at an affordable cost. I will describe the approach taken at Amalfi so that hospitals can have such a solution up and running in a few days of work for their IT departments, in what I think is an interesting combination of software engineering and automatic Machine Learning.
An intelligent assistant shall be an agent that knows you and the world, can receive your requests or predict your needs, and provide you the right services at the right time with your permission. As smart devices such as Amazon Alexa, Google Home, Ray-ban Meta get popular, Intelligent Assistants are gradually playing an important role in people's lives. The Emergence of wearable devices brings more opportunities and calls for the next generation of Intelligent Assistants. In this talk, we discuss the many challenges and opportunities we face to grow intelligent assistants from voice-only to multi-modal, from context-agnostic to context-aware, from listening to the users' requests to predicting the user's needs, and from server-side to on-device. We describe our LLM-based solutions toward multi-modality, contextualization, personalization, and retrieval-augmentation, and discuss how they are enabled on devices. We expect these new challenges to open doors to new research areas and start a new chapter for providing personal assistance services
Once a very large payment processor client told us: 'if we are down for 5 minutes, we open the evening news - so don't screw up'. Processing billions of dollars per day, many financial institutions, need to continuously fight organized crime in the form of transaction fraud, stolen cards, anti-money laundering, account opening fraud, impersonations scams, phishing, and many other exotic and ever changing attacks from organized crime groups worldwide. In fact, it is estimated that in 2023 the global losses in fraud scams and bank fraud reached 485.6 billion. However, in addition to having very good detection rates and very low false positive rates, financial institutions also need to maintain very high availability rates, very low latencies, very high throughputs, automatic fault tolerance, auto scale up and down, and more. In this talk we cover some lessons related to running ML models in harsh, mission critical environments. We describe data issues, scale issues, ethical issues, system issues, security issues, compliance issues, business and regulation issues, and some architectural tradeoffs and architectural evolutions.
Dynamic graph learning equips the edges with time attributes and allows multiple links between two nodes, which is a crucial technology for understanding evolving data scenarios like traffic prediction and recommendation systems. Existing works obtain the evolving patterns mainly depending on the most recent neighbor sequences. However, we argue that whether two nodes will have interaction with each other in the future is highly correlated with the same interaction that happened in the past. Only considering the recent neighbors overlooks the phenomenon of repeat behavior and fails to accurately capture the temporal evolution of interactions. To fill this gap, this paper presents RepeatMixer, which considers evolving patterns of first and high-order repeat behavior in the neighbor sampling strategy and temporal information learning. Firstly, we define the first-order repeat-aware nodes of the source node as the destination nodes that have interacted historically and extend this concept to high orders as nodes in the destination node's high-order neighbors. Then, we extract neighbors of the source node that interacted before the appearance of repeat-aware nodes with a slide window strategy as its neighbor sequence. Next, we leverage both the first and high-order neighbor sequences of source and destination nodes to learn temporal patterns of interactions via an MLP-based encoder. Furthermore, considering the varying temporal patterns on different orders, we introduce a time-aware aggregation mechanism that adaptively aggregates the temporal representations from different orders based on the significance of their interaction time sequences. Experimental results demonstrate the superiority of RepeatMixer over state-of-the-art models in link prediction tasks, underscoring the effectiveness of the proposed repeat-aware neighbor sampling strategy.
High-frequency trading (HFT) that executes algorithmic trading in short time scales, has recently occupied the majority of cryptocurrency market. Besides traditional quantitative trading methods, reinforcement learning (RL) has become another appealing approach for HFT due to its terrific ability of handling high-dimensional financial data and solving sophisticated sequential decision-making problems, e.g., hierarchical reinforcement learning (HRL) has shown its promising performance on second-level HFT by training a router to select only one sub-agent from the agent pool to execute the current transaction. However, existing RL methods for HFT still have some defects: 1) standard RL-based trading agents suffer from the overfitting issue, preventing them from making effective policy adjustments based on financial context; 2) due to the rapid changes in market conditions, investment decisions made by an individual agent are usually one-sided and highly biased, which might lead to significant loss in extreme markets. To tackle these problems, we propose a novel Memory Augmented Context-aware Reinforcement learning method On HFT, a.k.a. MacroHFT, which consists of two training phases: 1) we first train multiple types of sub-agents with the market data decomposed according to various financial indicators, specifically market trend and volatility, where each agent owns a conditional adapter to adjust its trading policy according to market conditions; 2) then we train a hyper-agent to mix the decisions from these sub-agents and output a consistently profitable meta-policy to handle rapid market fluctuations, equipped with a memory mechanism to enhance the capability of decision-making. Extensive experiments on various cryptocurrency markets demonstrate that MacroHFT can achieve state-of-the-art performance on minute-level trading tasks. Code has been released in https://github.com/ZONG0004/MacroHFT.
Graph contrastive learning is a representative self-supervised graph learning that has demonstrated excellent performance in learning node representations. Despite the extensive studies on graph contrastive learning models, most existing models are tailored to static graphs, hindering their application to real-world graphs which are often dynamically evolving. Directly applying these models to dynamic graphs brings in severe efficiency issues in repetitively updating the learned embeddings. To address this challenge, we propose IDOL, a novel contrastive learning framework for dynamic graph representation learning. IDOL conducts the graph propagation process based on a specially designed Personalized PageRank algorithm which can capture the topological changes incrementally. This effectively eliminates heavy recomputation while maintaining high learning quality. Our another main design is a topology-monitorable sampling strategy which lays the foundation of graph contrastive learning. We further show that the design in IDOL achieves a desired performance guarantee. Our experimental results on multiple dynamic graphs show that IDOL outperforms the strongest baselines on node classification tasks in various performance metrics.
Recent studies have highlighted fairness issues in Graph Neural Networks (GNNs), where they produce discriminatory predictions against specific protected groups categorized by sensitive attributes such as race and age. While various efforts to enhance GNN fairness have made significant progress, these approaches are often tailored to specific sensitive attributes. Consequently, they necessitate retraining the model from scratch to accommodate changes in the sensitive attribute requirement, resulting in high computational costs. To gain deeper insights into this issue, we approach the graph fairness problem from a causal modeling perspective, where we identify the confounding effect induced by the sensitive attribute as the underlying reason. Motivated by this observation, we formulate the fairness problem in graphs from an invariant learning perspective, which aims to learn invariant representations across environments. Accordingly, we propose a graph fairness framework based on invariant learning, namely FairINV, which enables the training of fair GNNs to accommodate various sensitive attributes within a single training session. Specifically, FairINV incorporates sensitive attribute partition and trains fair GNNs by eliminating spurious correlations between the label and various sensitive attributes. Experimental results on several real-world datasets demonstrate that FairINV significantly outperforms state-of-the-art fairness approaches, underscoring its effectiveness. Our code is available via: https://github.com/ZzoomD/FairINV/.
Generating trajectory data is among promising solutions to addressing privacy concerns, collection costs, and proprietary restrictions usually associated with human mobility analyses. However, existing trajectory generation methods are still in their infancy due to the inherent diversity and unpredictability of human activities, grappling with issues such as fidelity, flexibility, and generalizability. To overcome these obstacles, we propose ControlTraj, a Controllable Trajectory generation framework with the topology-constrained diffusion model. Distinct from prior approaches, ControlTraj utilizes a diffusion model to generate high-fidelity trajectories while integrating the structural constraints of road network topology to guide the geographical outcomes. Specifically, we develop a novel road segment autoencoder to extract fine-grained road segment embedding. The encoded features, along with trip attributes, are subsequently merged into the proposed geographic denoising UNet architecture, named GeoUNet, to synthesize geographic trajectories from white noise. Through experimentation across three real-world data settings, ControlTraj demonstrates its ability to produce human-directed, high-fidelity trajectory generation with adaptability to unexplored geographical contexts.
Problems in the area of distributed computing have been extensively studied. In this paper, we focus on the Distributed Thresholded Counting problem in the coordinator model. In this problem, we have k sites holding their input and communicating with a central coordinator. The coordinator's task is to determine whether the sum of inputs is larger than a threshold. While the communication complexity of this basic problem has been studied for decades, it is still not well understood. Our work considers the worst-case communication cost for an algorithm that uses limited interaction - i.e. a bounded number of rounds of communication. Algorithms in previous research usually need O(łogłog N) or O(k) rounds. In comparison, in the deterministic case, our algorithm achieves optimal communication complexity in only α(k) rounds, where α(k) denotes the inverse Ackermann function and is nearly constant. We also give a randomized algorithm that balances communication, rounds, and error probability.
The rise of social media has intensified fake news risks, prompting a growing focus on leveraging graph learning methods such as graph neural networks (GNNs) to understand post-spread patterns of news. However, existing methods often produce less robust and interpretable results as they assume that all information within the propagation graph is relevant to the news item, without adequately eliminating noise from engaged users. Furthermore, they inadequately capture intricate patterns inherent in long-sequence dependencies of news propagation due to their use of shallow GNNs aimed at avoiding the over-smoothing issue, consequently diminishing their overall accuracy. In this paper, we address these issues by proposing the Propagation Structure-aware Graph Transformer (PSGT). Specifically, to filter out noise from users within propagation graphs, PSGT first designs a noise-reduction self-attention mechanism based on the information bottleneck principle, aiming to minimize or completely remove the noise attention links among task-irrelevant users. Moreover, to capture multi-scale propagation structures while considering long-sequence features, we present a novel relational propagation graph as a position encoding for the graph Transformer, enabling the model to capture both propagation depth and distance relationships of users. Extensive experiments demonstrate the effectiveness, interpretability, and robustness of our PSGT.
Dynamic pricing, which suggests the optimal prices based on the dynamic demands, has received considerable attention in academia and industry. On online hotel booking platforms, room demand fluctuates due to various factors, notably hotel popularity and competition. In this paper, we propose a dynamic pricing approach with popularity and competitiveness-aware demand learning. Specifically, we introduce a novel demand function that incorporates popularity and competitiveness coefficients to comprehensively model the price elasticity of demand. We develop a dynamic demand prediction network that focuses on learning these coefficients in the proposed demand function, enhancing the interpretability and accuracy of price suggestion. The model is trained in a multi-task framework that effectively leverages the correlations of demands among groups of similar hotels to alleviate data sparseness in room-level occupancy prediction. Comprehensive experiments conducted on real-world datasets validate the superiority of our method over state-of-the-art baselines in both demand prediction and dynamic pricing. Our model has been successfully deployed on a popular online travel platform, serving tens of millions of users and hoteliers.
Large-scale vision-language (V-L) models have demonstrated remarkable generalization capabilities for downstream tasks through prompt tuning. However, the mechanisms behind the learned text representations are unknown, limiting further generalization gains, and the limitations are more severe when faced with the prevalent class imbalances seen in web-sourced datasets. Recent advances in the neural collapse (NC) phenomenon of vision-only models suggest that the optimal representation structure is the simplex ETF, which paves the way to study representations in V-L models. In this paper, we make the first attempt to use NC for examining the representations in V-L models via prompt tuning. It is found that NC optimality of text-to-image representations shows a positive correlation with downstream generalizability, which is more severe under class imbalance settings. To improve the representations, we propose Neural-collapse-anchored Prompt Tuning (NPT), a novel method that learns prompts with text and image representations that satisfy the same simplex Equiangular Tight Frame (ETF). NPT incorporates two regularization terms: language-modality collapse and multi-modality isomorphism; and it is compatible with other prompt tuning methods. Extensive experiments show that NPT can consistently help to improve existing prompt tuning techniques across 11 datasets for both balanced and imbalanced settings.
In causal inference, estimating heterogeneous treatment effects (HTE) is critical for identifying how different subgroups respond to interventions, with broad applications in fields such as precision medicine and personalized advertising. Although HTE estimation methods aim to improve accuracy, how to provide explicit subgroup descriptions remains unclear, hindering data interpretation and strategic intervention management. In this paper, we propose CURLS, a novel rule learning method leveraging HTE, which can effectively describe subgroups with significant treatment effects. Specifically, we frame causal rule learning as a discrete optimization problem, finely balancing treatment effect with variance and considering the rule interpretability. We design an iterative procedure based on the minorize-maximization algorithm and solve a submodular lower bound as an approximation for the original. Quantitative experiments and qualitative case studies verify that compared with state-of-the-art methods, CURLS can find subgroups where the estimated and true effects are 16.1% and 13.8% higher and the variance is 12.0% smaller, while maintaining similar or better estimation accuracy and rule interpretability. Code is available at https://osf.io/zwp2k/.
Synthesizing electronic health records (EHR) data has become a preferred strategy to address data scarcity, improve data quality, and model fairness in healthcare. However, existing approaches for EHR data generation predominantly rely on state-of-the-art generative techniques like generative adversarial networks, variational autoencoders, and language models. These methods typically replicate input visits, resulting in inadequate modeling of temporal dependencies between visits and overlooking the generation of time information, a crucial element in EHR data. Moreover, their ability to learn visit representations is limited due to simple linear mapping functions, thus compromising generation quality. To address these limitations, we propose a novel EHR data generation model called EHRPD. It is a diffusion-based model designed to predict the next visit based on the current one while also incorporating time interval estimation. To enhance generation quality and diversity, we introduce a novel time-aware visit embedding module and a pioneering predictive denoising diffusion probabilistic model (P-DDPM). Additionally, we devise a predictive U-Net (PU-Net) to optimize P-DDPM. We conduct experiments on two public datasets and evaluate EHRPD from fidelity, privacy, and utility perspectives. The experimental results demonstrate the efficacy and utility of the proposed EHRPD in addressing the aforementioned limitations and advancing EHR data generation.
Implicit graph neural networks have gained popularity in recent years as they capture long-range dependencies while improving predictive performance in static graphs. Despite the tussle between performance degradation due to the oversmoothing of learned embeddings and long-range dependency being more pronounced in dynamic graphs, as features are aggregated both across neighborhood and time, no prior work has proposed an implicit graph neural model in a dynamic setting. In this paper, we present Implicit Dynamic Graph Neural Network (IDGNN) a novel implicit neural network for dynamic graphs which is the first of its kind. A key characteristic of IDGNN is that it demonstrably is well-posed, i.e., it is theoretically guaranteed to have a fixed-point representation. We then demonstrate that the standard iterative algorithm often used to train implicit models is computationally expensive in our dynamic setting as it involves computing gradients, which themselves have to be estimated in an iterative manner. To overcome this, we pose an equivalent bilevel optimization problem and propose an efficient single-loop training algorithm that avoids iterative computation by maintaining moving averages of key components of the gradients. We conduct extensive experiments on real-world datasets on both classification and regression tasks to demonstrate the superiority of our approach over state-of-the-art baselines. We also demonstrate that our bi-level optimization framework maintains the performance of the expensive iterative algorithm while obtaining up to 1600x speed-up.