Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation

Recommender system usually suffers from severe popularity bias -- the collected interaction data usually exhibits quite imbalanced or even long-tailed distribution over items. Such skewed distribution may result from the users conformity to the group, which deviates from reflecting users true preference. Existing efforts for tackling this issue mainly focus on completely eliminating popularity bias. However, we argue that not all popularity bias is evil. Popularity bias not only results from conformity but also item quality, which is usually ignored by existing methods. Some items exhibit higher popularity as they have intrinsic better property. Blindly removing the popularity bias would lose such important signal, and further deteriorate model performance. To sufficiently exploit such important information for recommendation, it is essential to disentangle the benign popularity bias caused by item quality from the harmful popularity bias caused by conformity. Although important, it is quite challenging as we lack an explicit signal to differentiate the two factors of popularity bias. In this paper, we propose to leverage temporal information as the two factors exhibit quite different patterns along the time: item quality revealing item inherent property is stable and static while conformity that depends on items recent clicks is highly time-sensitive. Correspondingly, we further propose a novel Time-aware DisEntangled framework (TIDE), where a click is generated from three components namely the static item quality, the dynamic conformity effect, as well as the user-item matching score returned by any recommendation model. Lastly, we conduct interventional inference such that the recommendation can benefit from the benign popularity bias while circumvent the harmful one. Extensive experiments on three real-world datasets demonstrated the effectiveness of TIDE.

PandaDB: Understanding Unstructured Data in Graph Database

At present, graph model is widely used in many applications, such as knowledge graph, financial anti-fraud. Unstructured data(such as images, videos, and audios) is under explosive growing. So, queries of unstructured data content on graph are widespread in a rich vein of real-world applications. Many graph database systems have started to support unstructured data to meet such demands. However, queries over structured and unstructured data on graph are often treated as separate tasks in most systems. These tasks are executed on different module of the tools chain. Collaborative queries (i.e., involving both data types) are not yet fully supported.This paper proposes a graph database supporting collaborative queries on property graph, named PandaDB. Its to fulfill the emerging demands about querying unstructured data on property graph model. PandaDB introduces CypherPlus, a query language which enables the users to express collaborative queries using cypher semantics by introducing sub-property and a series of logical operators. PandaDB is built based on Neo4j, manage the unstructured data in the format of BLOB. The computable pattern is proposed to introduce the content of unstructured data into computation. Moreover, to support the large-scale query, this paper proposes the semantic index, cache and index the extracted computable pattern. The collaborative query on graph is optimized by the min-cost optimization method. Experimental results on both public and in-house datasets show the performance achieved by PandaDB and its effectiveness.

Communication Efficient Federated Learning with Adaptive Quantization

Federated learning (FL) has attracted tremendous attentions in recent years due to its privacy preserving measures and great potentials in some distributed but privacy-sensitive applications like finance and health. However, high communication overloads for transmitting high-dimensional networks and extra security masks remains a bottleneck of FL. This paper proposes a communication-efficient FL framework with Adaptive Quantized Gradient (AQG) which adaptively adjusts the quantization level based on local gradients update to fully utilize the heterogeneousness of local data distribution for reducing unnecessary transmissions. Besides, the client dropout issues are taken into account and the Augmented AQG is developed, which could limit the dropout noise with an appropriate amplification mechanism for transmitted gradients. Theoretical analysis and experiment results show that the proposed AQG leads to 25%-50% of additional transmission reduction as compared to existing popular methods including Quantized Gradient Descent (QGD) and Lazily Aggregated Quantized (LAQ) gradient-based method without deteriorating convergence properties. Particularly, experiments with heterogenous data distributions corroborate a more significant transmission reduction compared with independent identical data distributions. Meanwhile, the proposed AQG is robust to a client dropping rate up to 90% empirically, and the Augmented AQG manages to further improve the FL systems communication efficiency with the presence of moderate-scale client dropouts commonly seen in practical FL scenarios.

Exploring Evolving Plants as Interacting Particles in a Randomly Generated Heterogeneous Environment

We model evolution of plants in a world, made up of different locations, with multiple environments (mutually exclusive and collectively exhaustive subsets of locations). Each environment (landmass) has temperature, rainfall, and other attributes that directly affect plant growth and reproduction. Each plant has preferences for environment attributes. Depending on how suitable the environment is to the plants, seeds are released or death occurs. With every reproductive cycle, genetic mutations occur. To model competition, plants in compete for survival, and success is stochastically dependent on environmental fitness. Our model determines whether and how evolution occurs, and how the attributes of plants change and possibly converge over time in relation to the attributes of the environment.

Spontaneous laser line sweeping in bi-directional ring thulium fiber laser

We report a phenomenon of self-sweeping in a bi-directional ring thulium-doped fiber laser, for the first time. The laser is spontaneously sweeping in both directions at a rate up to 0.2 nm/s with 15 nm sweeping range in 1.95 {mu}m wavelength region. The laser output is switchable between two different working modes: periodical spontaneous laser line sweeping with generation of microsecond pulses in time domain; or static central wavelength with amplitude modulated temporally.