The application of mixture-of-experts (MoE) is gaining popularity due to its ability to improve model's performance. In an MoE structure, the gate layer plays a significant role in distinguishing and routing input features to different experts. This enables each expert to specialize in processing their corresponding sub-tasks. However, the gate's routing mechanism also gives rise to narrow vision: the individual MoE's expert fails to use more samples in learning the allocated sub-task, which in turn limits the MoE to further improve its generalization ability. To effectively address this, we propose a method called Mixture-of-Distilled-Expert (MoDE), which applies moderate mutual distillation among experts to enable each expert to pick up more features learned by other experts and gain more accurate perceptions on their original allocated sub-tasks. We conduct plenty experiments including tabular, NLP and CV datasets, which shows MoDE's effectiveness, universality and robustness. Furthermore, we develop a parallel study through innovatively constructing "expert probing", to experimentally prove why MoDE works: moderate distilling knowledge can improve each individual expert's test performances on their assigned tasks, leading to MoE's overall performance improvement.
Given the enormous number of users and items, industrial cascade recommendation systems (RS) are continuously expanded in size and complexity to deliver relevant items, such as news, services, and commodities, to the appropriate users. In a real-world scenario with hundreds of thousands requests per second, significant computation is required to infer personalized results for each request, resulting in a massive energy consumption and carbon emission that raises concern. This paper proposes GreenFlow, a practical computation allocation framework for RS, that considers both accuracy and carbon emission during inference. For each stage (e.g., recall, pre-ranking, ranking, etc.) of a cascade RS, when a user triggers a request, we define two actions that determine the computation: (1) the trained instances of models with different computational complexity; and (2) the number of items to be inferred in the stage. We refer to the combinations of actions in all stages as action chains. A reward score is estimated for each action chain, followed by dynamic primal-dual optimization considering both the reward and computation budget. Extensive experiments verify the effectiveness of the framework, reducing computation consumption by 41% in an industrial mobile application while maintaining commercial revenue. Moreover, the proposed framework saves approximately 5000kWh of electricity and reduces 3 tons of carbon emissions per day.
In this work, we propose FastCoT, a model-agnostic framework based on parallel decoding without any further training of an auxiliary model or modification to the LLM itself. FastCoT uses a size-varying context window whose size changes with position to conduct parallel decoding and auto-regressive decoding simultaneously, thus fully utilizing GPU computation resources. In FastCoT, the parallel decoding part provides the LLM with a quick glance of the future composed of approximate tokens, which could lead to faster answers compared to regular autoregressive decoding used by causal transformers. We also provide an implementation of parallel decoding within LLM, which supports KV-cache generation and batch processing. Through extensive experiments, we demonstrate that FastCoT saves inference time by nearly 20% with only a negligible performance drop compared to the regular approach. Additionally, we show that the context window size exhibits considerable robustness for different tasks.
Finding node correspondence across networks, namely multi-network alignment, is an essential prerequisite for joint learning on multiple networks. Despite great success in aligning networks in pairs, the literature on multi-network alignment is sparse due to the exponentially growing solution space and lack of high-order discrepancy measures. To fill this gap, we propose a hierarchical multi-marginal optimal transport framework named HOT for multi-network alignment. To handle the large solution space, multiple networks are decomposed into smaller aligned clusters via the fused Gromov-Wasserstein (FGW) barycenter. To depict high-order relationships across multiple networks, the FGW distance is generalized to the multi-marginal setting, based on which networks can be aligned jointly. A fast proximal point method is further developed with guaranteed convergence to a local optimum. Extensive experiments and analysis show that our proposed HOT achieves significant improvements over the state-of-the-art in both effectiveness and scalability.
User-side group fairness is crucial for modern recommender systems, as it aims to alleviate performance disparity between groups of users defined by sensitive attributes such as gender, race, or age. We find that the disparity tends to persist or even increase over time. This calls for effective ways to address user-side fairness in a dynamic environment, which has been infrequently explored in the literature. However, fairness-constrained re-ranking, a typical method to ensure user-side fairness (i.e., reducing performance disparity), faces two fundamental challenges in the dynamic setting: (1) non-differentiability of the ranking-based fairness constraint, which hinders the end-to-end training paradigm, and (2) time-inefficiency, which impedes quick adaptation to changes in user preferences. In this paper, we propose FAir Dynamic rEcommender (FADE), an end-to-end framework with fine-tuning strategy to dynamically alleviate performance disparity. To tackle the above challenges, FADE uses a novel fairness loss designed to be differentiable and lightweight to fine-tune model parameters to ensure both user-side fairness and high-quality recommendations. Via extensive experiments on the real-world dataset, we empirically demonstrate that FADE effectively and efficiently reduces performance disparity, and furthermore, FADE improves overall recommendation quality over time compared to not using any new data.
Class imbalance is prevalent in real-world node classification tasks and often biases graph learning models toward majority classes. Most existing studies root from a node-centric perspective and aim to address the class imbalance in training data by node/class-wise reweighting or resampling. In this paper, we approach the source of the class-imbalance bias from an under-explored topology-centric perspective. Our investigation reveals that beyond the inherently skewed training class distribution, the graph topology also plays an important role in the formation of predictive bias: we identify two fundamental challenges, namely ambivalent and distant message-passing, that can exacerbate the bias by aggravating majority-class over-generalization and minority-class misclassification. In light of these findings, we devise a lightweight topological augmentation method ToBA to dynamically rectify the nodes influenced by ambivalent/distant message-passing during graph learning, so as to mitigate the class-imbalance bias. We highlight that ToBA is a model-agnostic, efficient, and versatile solution that can be seamlessly combined with and further boost other imbalance-handling techniques. Systematic experiments validate the superior performance of ToBA in both promoting imbalanced node classification and mitigating the prediction bias between different classes.
Unsupervised Anomaly Detection (UAD) is a key data mining problem owing to its wide real-world applications. Due to the complete absence of supervision signals, UAD methods rely on implicit assumptions about anomalous patterns (e.g., scattered/sparsely/densely clustered) to detect anomalies. However, real-world data are complex and vary significantly across different domains. No single assumption can describe such complexity and be valid in all scenarios. This is also confirmed by recent research that shows no UAD method is omnipotent. Based on above observations, instead of searching for a magic universal winner assumption, we seek to design a general UAD Booster (UADB) that empowers any UAD models with adaptability to different data. This is a challenging task given the heterogeneous model structures and assumptions adopted by existing UAD methods. To achieve this, we dive deep into the UAD problem and find that compared to normal data, anomalies (i) lack clear structure/pattern in feature space, thus (ii) harder to learn by model without a suitable assumption, and finally, leads to (iii) high variance between different learners. In light of these findings, we propose to (i) distill the knowledge of the source UAD model to an imitation learner (booster) that holds no data assumption, then (ii) exploit the variance between them to perform automatic correction, and thus (iii) improve the booster over the original UAD model. We use a neural network as the booster for its strong expressive power as a universal approximator and ability to perform flexible post-hoc tuning. Note that UADB is a model-agnostic framework that can enhance heterogeneous UAD models in a unified way. Extensive experiments on over 80 tabular datasets demonstrate the effectiveness of UADB.
Many payment platforms hold large-scale marketing campaigns, which allocate incentives to encourage users to pay through their applications. To maximize the return on investment, incentive allocations are commonly solved in a two-stage procedure. After training a response estimation model to estimate the users' mobile payment probabilities (MPP), a linear programming process is applied to obtain the optimal incentive allocation. However, the large amount of biased data in the training set, generated by the previous biased allocation policy, causes a biased estimation. This bias deteriorates the performance of the response model and misleads the linear programming process, dramatically degrading the performance of the resulting allocation policy. To overcome this obstacle, we propose a bias correction adversarial network. Our method leverages the small set of unbiased data obtained under a full-randomized allocation policy to train an unbiased model and then uses it to reduce the bias with adversarial learning. Offline and online experimental results demonstrate that our method outperforms state-of-the-art approaches and significantly improves the performance of the resulting allocation policy in a real-world marketing campaign.
Imbalanced Learning (IL) is an important problem that widely exists in data mining applications. Typical IL methods utilize intuitive class-wise resampling or reweighting to directly balance the training set. However, some recent research efforts in specific domains show that class-imbalanced learning can be achieved without class-wise manipulation. This prompts us to think about the relationship between the two different IL strategies and the nature of the class imbalance. Fundamentally, they correspond to two essential imbalances that exist in IL: the difference in quantity between examples from different classes as well as between easy and hard examples within a single class, i.e., inter-class and intra-class imbalance. Existing works fail to explicitly take both imbalances into account and thus suffer from suboptimal performance. In light of this, we present Duple-Balanced Ensemble, namely DUBE , a versatile ensemble learning framework. Unlike prevailing methods, DUBE directly performs inter-class and intra-class balancing without relying on heavy distance-based computation, which allows it to achieve competitive performance while being computationally efficient. We also present a detailed discussion and analysis about the pros and cons of different inter/intra-class balancing strategies based on DUBE . Extensive experiments validate the effectiveness of the proposed method. Code and examples are available at https://github.com/ICDE2022Sub/duplebalance.
imbalanced-ensemble, abbreviated as imbens, is an open-source Python toolbox for quick implementing and deploying ensemble learning algorithms on class-imbalanced data. It provides access to multiple state-of-art ensemble imbalanced learning (EIL) methods, visualizer, and utility functions for dealing with the class imbalance problem. These ensemble methods include resampling-based, e.g., under/over-sampling, and reweighting-based ones, e.g., cost-sensitive learning. Beyond the implementation, we also extend conventional binary EIL algorithms with new functionalities like multi-class support and resampling scheduler, thereby enabling them to handle more complex tasks. The package was developed under a simple, well-documented API design follows that of scikit-learn for increased ease of use. imbens is released under the MIT open-source license and can be installed from Python Package Index (PyPI). Source code, binaries, detailed documentation, and usage examples are available at https://github.com/ZhiningLiu1998/imbalanced-ensemble.