Knowledge graphs (KGs) have become vitally important in modern recommender
systems, effectively improving performance and interpretability. Fundamentally,
recommender systems aim to identify user interests based on historical
interactions and recommend suitable items. However, existing works overlook two
key challenges: (1) an interest corresponds to a potentially large set of
related items, and (2) the lack of explicit, fine-grained exploitation of KG
information and interest connectivity. This leads to an inability to reflect
distinctions between entities and interests when modeling them in a single way.
Additionally, the granularity of concepts in the knowledge graphs used for
recommendations tends to be coarse, failing to match the fine-grained nature of
user interests. This homogenization limits the precise exploitation of
knowledge graph data and interest connectivity. To address these limitations,
we introduce a novel embedding-based model called InBox. Specifically, various
knowledge graph entities and relations are embedded as points or boxes, while
user interests are modeled as boxes encompassing interaction history.
Representing interests as boxes enables containing collections of item points
related to that interest. We further propose that an interest comprises diverse
basic concepts, and box intersection naturally supports concept combination.
Across three training steps, InBox significantly outperforms state-of-the-art
methods like HAKG and KGIN on recommendation tasks. Further analysis provides
meaningful insights into the variable value of different KG data for
recommendations. In summary, InBox advances recommender systems through
box-based interest and concept modeling for sophisticated knowledge graph
exploitation.

通过盒子形式的兴趣和概念建模，InBox 推动推荐系统的发展，以实现对知识图谱的复杂利用。

使用知识图谱和兴趣盒嵌入进行推荐

InBox: Recommendation with Knowledge Graph using Interest Box Embedding

We address the problem of class incremental learning, which is a core step
towards achieving adaptive vision intelligence. In particular, we consider the
task setting of incremental learning with limited memory and aim to achieve
better stability-plasticity trade-off. To this end, we propose a novel
two-stage learning approach that utilizes a dynamically expandable
representation for more effective incremental concept modeling. Specifically,
at each incremental step, we freeze the previously learned representation and
augment it with additional feature dimensions from a new learnable feature
extractor. This enables us to integrate new visual concepts with retaining
learned knowledge. We dynamically expand the representation according to the
complexity of novel concepts by introducing a channel-level mask-based pruning
strategy. Moreover, we introduce an auxiliary loss to encourage the model to
learn diverse and discriminate features for novel concepts. We conduct
extensive experiments on the three class incremental learning benchmarks and
our method consistently outperforms other methods with a large margin.

提出了一种新颖的、两阶段的学习方法，利用动态可扩展表示进行更有效的概念建模，在三个类别的增量学习基准测试中，该方法始终表现出比其他方法更好很大的优势。

DER：动态可扩展表示用于类增量学习

DER: Dynamically Expandable Representation for Class Incremental  Learning

We elaborate a theory for the modeling of concepts using the mathematical
structure of quantum mechanics. Concepts are represented by vectors in the
complex Hilbert space of quantum mechanics and membership weights of items are
modeled by quantum weights calculated following the quantum rules. We apply
this theory to model the disjunction of concepts and show that experimental
data of membership weights of items with respect to the disjunction of concepts
can be modeled accurately. It is the quantum effects of interference and
superposition, combined with an effect of context, that are at the origin of
the effects of overextension and underextension observed as deviations from a
classical use of the disjunction. We put forward a graphical explanation of the
effects of overextension and underextension by interpreting the quantum model
applied to the modeling of the disjunction of concepts.

利用量子力学的数学结构来建模概念，将概念通过量子态空间中的向量进行表示，利用量子规则计算量子权重来建模项目的成员权重，然后将该理论应用于模拟概念或关系的分离，并证明这种方法在实验数据上可以准确地建模，这种超杂化和欠杂化的现象是由于量子干涉和叠加效应，结合了上下文的效应而导致的，该论文为这些效应提供了图形解释。